© 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. 77700
    Prev
    Next
    INDEX
    Explanations

    Code and technical text

    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
    Itoa
    -0.57
     avanti
    -0.46
     originais
    -0.44
    ษัท
    -0.44
    Sullivan
    -0.43
     bakgrund
    -0.42
     запа
    -0.42
     آور
    -0.41
     NSCoder
    -0.41
    رشف
    -0.41
    POSITIVE LOGITS
     zer
    0.63
    सन्दर्भ
    0.62
     Италијани
    0.60
    BASEPATH
    0.59
     >=",
    0.56
    ümmer
    0.55
     initComponents
    0.53
     jScrollPane
    0.53
    matchCondition
    0.52
    oplayer
    0.52
    Activations Density 0.000%

    No Known Activations