© 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. 4418
    Prev
    Next
    INDEX
    Explanations

    phrases related to desires or wants

    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
    1978
    +0.10
    0.3%
    791
    +0.07
    0.2%
    674
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.10
    0.05
    862
    +0.07
    0.02
    1509
    +0.07
    0.03
    Negative Logits
     apprehen
    -1.36
     gaily
    -1.21
     unspeak
    -1.14
     disagre
    -1.11
     philanth
    -1.10
     shenan
    -1.09
     McLaugh
    -1.08
     depic
    -1.04
     unlaw
    -1.04
     Middles
    -1.03
    POSITIVE LOGITS
     needed
    0.71
    needed
    0.69
    Desired
    0.68
    Needed
    0.65
    waitKey
    0.61
     Topf
    0.61
    desired
    0.60
     desired
    0.60
     wanted
    0.58
     deserve
    0.57
    Activations Density 0.171%

    No Known Activations