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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 19986
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of incitement or encouragement

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <strong>
    -0.82
     Wheeler
    -0.72
    ⑦
    -0.68
     Sharma
    -0.68
     Salas
    -0.67
     Waterman
    -0.63
     Bullock
    -0.63
     Brito
    -0.63
    prefetch
    -0.63
    atch
    -0.59
    POSITIVE LOGITS
     INC
    1.32
    inc
    1.21
    Inc
    1.19
     inc
    1.18
    lapsingToolbar
    1.13
    INC
    1.12
    awtextra
    1.09
     Inc
    1.07
     numberWith
    1.01
     Cresc
    0.99
    Activations Density 0.011%

    No Known Activations