© 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. 4-CLT-HP
    7. 285
    Prev
    Next
    INDEX
    Explanations

    Code

    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
    áž
    -0.56
    inscrire
    -0.54
     surla
    -0.54
     pendaftaran
    -0.54
     risico
    -0.52
    ieteur
    -0.52
     putter
    -0.50
    hésite
    -0.50
    scription
    -0.49
     achtergrond
    -0.49
    POSITIVE LOGITS
     insuffisamment
    0.48
    ⓧ
    0.48
     виправивши
    0.47
     ohr
    0.47
    AddWithValue
    0.45
    forChild
    0.45
    expandindo
    0.44
    ener
    0.44
    acam
    0.44
    AMP
    0.43
    Activations Density 0.007%

    No Known Activations