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. 12720
    Prev
    Next
    INDEX
    Explanations

    H

    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
    verifyException
    -0.53
    icoot
    -0.47
    বহ
    -0.44
     ostavi
    -0.43
    querade
    -0.43
     his
    -0.42
    klär
    -0.42
    dub
    -0.41
    putable
    -0.41
    STERY
    -0.41
    POSITIVE LOGITS
     itſelf
    0.71
     Telex
    0.68
    ArgsConstructor
    0.66
    CloseOperation
    0.65
    Rhestr
    0.64
     lye
    0.63
    клопе
    0.63
     heirs
    0.61
     Houſe
    0.60
     Hogar
    0.60
    Activations Density 0.020%

    No Known Activations