© 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. 42419
    Prev
    Next
    INDEX
    Explanations

    Namely

    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
    stris
    -0.65
    ronique
    -0.53
     Grüsse
    -0.49
    ADELPHIA
    -0.49
     Strasse
    -0.45
    EIP
    -0.43
    polazione
    -0.43
    brigens
    -0.42
    Werdegang
    -0.42
    trui
    -0.42
    POSITIVE LOGITS
     Administrativna
    0.77
     '\\;'
    0.71
     isos
    0.69
    multer
    0.66
     beijo
    0.64
    таратура
    0.64
     nakalista
    0.64
     peito
    0.63
     rús
    0.63
     Bare
    0.61
    Activations Density 0.798%

    No Known Activations