© 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. 2-RES-MATRYOSHKA-DC
    7. 7308
    Prev
    Next
    INDEX
    Explanations

    expressions related to physical violence or aggressive actions

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebElementEntity
    -0.59
     atenção
    -0.56
     écoulé
    -0.55
    principalTable
    -0.53
    انيف
    -0.52
     doccia
    -0.52
    ☆☆☆☆
    -0.52
     Einf
    -0.52
    insatz
    -0.52
     Obrador
    -0.50
    POSITIVE LOGITS
     kick
    3.72
     Kick
    3.30
    kick
    3.25
     kicks
    3.23
    Kick
    3.22
     kicked
    3.20
     kicking
    3.06
     KICK
    3.05
    kicks
    2.63
     Kicks
    2.47
    Activations Density 0.005%

    No Known Activations