© 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. 20-CLT-HP
    7. 72683
    Prev
    Next
    INDEX
    Explanations

    con

    np_max-act-logits · 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
    awtextra
    -0.82
    )‏
    -0.76
    Xna
    -0.65
    apimachinery
    -0.65
     protoimpl
    -0.65
    UnknownFields
    -0.65
     viewType
    -0.64
     <>",
    -0.64
    >//
    -0.64
    abestanden
    -0.64
    POSITIVE LOGITS
    mul
    0.42
    Atmos
    0.41
    tic
    0.40
    uti
    0.39
    mige
    0.37
     Akshay
    0.36
    moc
    0.35
    蒙
    0.35
     ég
    0.35
    Waff
    0.35
    Activations Density 0.000%

    No Known Activations