© 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. 94930
    Prev
    Next
    INDEX
    Explanations

    landfill

    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
     للمعارف
    -0.83
     Administrativna
    -0.79
     مشين
    -0.71
    rawDesc
    -0.70
    RectangleBorder
    -0.68
     оригіналу
    -0.68
    actéristique
    -0.68
    ("")]
    -0.67
    __(/*!
    -0.66
     ligiloj
    -0.65
    POSITIVE LOGITS
    s
    1.41
    ی
    0.70
    a
    0.65
    sup
    0.61
    sj
    0.58
    S
    0.57
    sy
    0.57
    sz
    0.56
    D
    0.56
    sP
    0.55
    Activations Density 1.567%

    No Known Activations