© 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. 4133
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical harm or aggressive actions

    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
    198
    +0.10
    0.3%
    297
    +0.09
    0.3%
    820
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1055
    +0.10
    0.05
    667
    +0.09
    0.04
    1823
    +0.09
    0.04
    Negative Logits
     utop
    -0.94
     solidar
    -0.83
     ideolog
    -0.79
     palet
    -0.74
     psychiat
    -0.74
     teras
    -0.74
     klu
    -0.73
     granada
    -0.73
     logis
    -0.71
     plati
    -0.67
    POSITIVE LOGITS
     outlander
    0.98
     hairc
    0.98
     snoopy
    0.95
     milf
    0.94
     oreo
    0.92
     parch
    0.91
     frow
    0.89
     reluct
    0.88
     scottish
    0.87
     gaily
    0.87
    Activations Density 0.284%

    No Known Activations