© 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. 0-CLT-HP
    7. 42678
    Prev
    Next
    INDEX
    Explanations

    destruction and errors

    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
     purpoſe
    -0.73
     Majefty
    -0.72
     pleaſure
    -0.71
     ſmall
    -0.71
     worshi
    -0.70
     throats
    -0.69
     vaiz
    -0.68
     itſelf
    -0.66
     quelcon
    -0.65
     ſeveral
    -0.65
    POSITIVE LOGITS
    ValueStyle
    0.86
    s
    0.65
     Vikipedi
    0.56
    Composable
    0.56
    Personensuche
    0.53
     et
    0.52
    __":
    0.48
    tencent
    0.47
     Terraria
    0.47
    rías
    0.47
    Activations Density 0.594%

    No Known Activations