© 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. 94754
    Prev
    Next
    INDEX
    Explanations

    Library

    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
    st
    -0.43
    th
    -0.43
    si
    -0.41
    anj
    -0.41
    SharedCtor
    -0.41
    e
    -0.40
    ors
    -0.40
     transfers
    -0.40
    3
    -0.40
     JADX
    -0.39
    POSITIVE LOGITS
    AnchorStyles
    0.76
     pauvres
    0.75
    CodedInputStream
    0.73
     виправивши
    0.73
    closedir
    0.72
    цездатний
    0.71
     فريبيس
    0.70
    väg
    0.70
     profondità
    0.70
     stället
    0.69
    Activations Density 0.017%

    No Known Activations