© 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. 1-CLT-HP
    7. 14493
    Prev
    Next
    INDEX
    Explanations

    committing harm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Audiodateien
    -0.53
     communes
    -0.51
    IntoConstraints
    -0.49
     investment
    -0.48
     Investment
    -0.48
     phosphat
    -0.47
    aarrggbb
    -0.47
    ыгана
    -0.47
    Investment
    -0.45
     okazji
    -0.45
    POSITIVE LOGITS
    toBe
    0.56
    QUID
    0.51
     înc
    0.49
    revision
    0.49
    RetentionPolicy
    0.49
     hof
    0.49
     bata
    0.48
     vore
    0.48
    сторі
    0.48
    addTab
    0.48
    Activations Density 0.014%

    No Known Activations