© 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. 3157
    Prev
    Next
    INDEX
    Explanations

    references to abuse or misuse of discretion

    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
     Sinks
    -0.58
    ั้ง
    -0.56
    aso
    -0.56
     Pocket
    -0.53
    pocket
    -0.53
    actionBar
    -0.53
    import
    -0.52
     Sten
    -0.52
    tagHelperRunner
    -0.52
    tsky
    -0.52
    POSITIVE LOGITS
     abuse
    3.09
     Abuse
    2.81
    abuse
    2.73
    Abuse
    2.63
     abused
    2.52
     abusing
    2.38
     abuses
    2.16
     abuso
    1.85
     abusers
    1.84
     abusive
    1.77
    Activations Density 0.016%

    No Known Activations