© 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. 43408
    Prev
    Next
    INDEX
    Explanations

    as

    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
     itſelf
    -0.70
     ويكيميديا
    -0.63
     BoxDecoration
    -0.60
     photolibrary
    -0.60
     againſt
    -0.59
    TemporalType
    -0.58
    isiä
    -0.57
     honom
    -0.57
    väg
    -0.57
    évaluateur
    -0.57
    POSITIVE LOGITS
     much
    0.59
     follows
    0.55
     as
    0.54
     follow
    0.53
     save
    0.51
    Referencer
    0.48
     part
    0.47
     little
    0.47
    {'
    0.46
    kais
    0.46
    Activations Density 0.034%

    No Known Activations