© 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. 42823
    Prev
    Next
    INDEX
    Explanations

    Repetition and code concepts

    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
     phrases
    -0.69
     Phrases
    -0.66
    ه
    -0.62
    S
    -0.59
    es
    -0.59
    e
    -0.58
    in
    -0.57
    E
    -0.57
    en
    -0.54
    ISTIC
    -0.52
    POSITIVE LOGITS
    Personendaten
    0.74
    XMLSchema
    0.70
    دانشنامهٔ
    0.63
     дописавши
    0.63
    cheibe
    0.60
     Reverso
    0.57
    %")
    0.56
    Hentet
    0.55
     للمعارف
    0.54
    ритори
    0.52
    Activations Density 0.037%

    No Known Activations