© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 3950
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal issues and investigations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    453
    +0.12
    0.4%
    776
    +0.10
    0.3%
    856
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1933
    +0.12
    0.02
    1929
    +0.10
    0.03
    225
    +0.10
    0.03
    Negative Logits
    Gön
    -0.70
    Panamoan
    -0.63
     disambiguazione
    -0.56
    tonsoft
    -0.55
    getMinutes
    -0.55
     TextAppearance
    -0.53
    HideFlags
    -0.53
    AutoScaleMode
    -0.52
    )++;
    -0.52
    canestro
    -0.52
    POSITIVE LOGITS
     maneu
    1.11
     disreg
    0.98
     intermitt
    0.98
     strick
    0.95
     stickied
    0.93
     kraken
    0.93
     shenan
    0.89
     attemp
    0.89
     crossfit
    0.88
     juke
    0.86
    Activations Density 0.108%

    No Known Activations