Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12733
    Prev
    Next
    INDEX
    Explanations

    Identifying markers

    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
     signature
    -1.08
    signature
    -1.03
     signatures
    -0.95
    signatures
    -0.94
     Signature
    -0.93
     Signatures
    -0.91
     SIGNATURE
    -0.90
    Signature
    -0.85
    WebMethod
    -0.84
    UrlResolution
    -0.84
    POSITIVE LOGITS
    Външни
    0.48
    DockStyle
    0.41
     quoc
    0.41
     developer
    0.39
    Siv
    0.38
    ña
    0.38
    dff
    0.37
     Conseils
    0.36
    sei
    0.36
    fler
    0.36
    Activations Density 0.004%

    No Known Activations