© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4275
    Prev
    Next
    INDEX
    Explanations

    time duration

    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
    positor
    -0.46
    VIR
    -0.44
    ázquez
    -0.42
    ={({
    -0.41
    minipage
    -0.40
    Char
    -0.40
    pptx
    -0.39
     mascul
    -0.39
    []
    -0.39
     صوتيه
    -0.38
    POSITIVE LOGITS
    djangoproject
    0.90
     numerus
    0.73
    ftagPool
    0.68
    RuleContext
    0.67
    例句
    0.66
     extranjero
    0.63
     aéreas
    0.62
    ьаж
    0.62
     '\\;'
    0.62
    archiviato
    0.62
    Activations Density 0.000%

    No Known Activations