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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14652
    Prev
    Next
    INDEX
    Explanations

    negative sentiments related to political events or conflicts

    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
    856
    +0.19
    0.6%
    1177
    +0.09
    0.3%
    946
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    856
    +0.19
    0.04
    1552
    +0.09
    0.04
    1473
    +0.09
    0.02
    Negative Logits
     tupperware
    -0.94
     cushi
    -0.88
     scrat
    -0.87
     cabrio
    -0.86
     guarante
    -0.84
     hairc
    -0.83
     eiffel
    -0.81
     reluct
    -0.80
     affor
    -0.79
     fusible
    -0.77
    POSITIVE LOGITS
     CiNii
    0.82
     PLWABN
    0.73
     elsewhere
    0.71
     another
    0.65
     виправивши
    0.63
    another
    0.63
     SUDOC
    0.62
     Another
    0.62
    Elsewhere
    0.62
    IsContent
    0.62
    Activations Density 0.247%

    No Known Activations