© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 95496
    Prev
    Next
    INDEX
    Explanations

    code/file paths

    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
    hists
    -1.33
    oner
    -1.10
    physis
    -0.72
    lains
    -0.70
    ChildScrollView
    -0.52
     CPA
    -0.50
     TextInputType
    -0.47
    RemoteException
    -0.47
    s
    -0.47
    expandindo
    -0.46
    POSITIVE LOGITS
     betweenstory
    0.77
    gants
    0.60
     Barnabas
    0.60
     חיצוניים
    0.58
     manqué
    0.58
     Ananda
    0.58
    omsday
    0.57
    monials
    0.56
    giene
    0.55
     Arka
    0.55
    Activations Density 1.526%

    No Known Activations