© 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. 5-CLT-HP
    7. 5689
    Prev
    Next
    INDEX
    Explanations

    Sophie/Sophia

    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
    ReusableCell
    -0.55
    saraba
    -0.52
    তথ্যসূত্র
    -0.51
    الحياه
    -0.50
     Flows
    -0.44
    Kaynakça
    -0.44
    ThroughAttribute
    -0.43
    tonode
    -0.42
    ignez
    -0.41
    quias
    -0.41
    POSITIVE LOGITS
     Xeon
    0.60
    uxxxx
    0.59
    $
    0.58
    ScopeManager
    0.56
    URLException
    0.56
    jalá
    0.55
    jsonwebtoken
    0.55
     AspNetCore
    0.53
     onAnimation
    0.53
    lwjgl
    0.52
    Activations Density 0.001%

    No Known Activations