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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-CLT-HP
    4. 74351
    Prev
    Next
    INDEX
    Explanations

    code and programming

    np_max-act-logits · 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
    bootstrapcdn
    -0.63
     CanadaChoose
    -0.63
     ContentValues
    -0.61
     devriez
    -0.59
    protoimpl
    -0.57
    Παραπομπές
    -0.57
    +#+#
    -0.57
    uttavia
    -0.57
     disambiguazione
    -0.57
     Substances
    -0.56
    POSITIVE LOGITS
     good
    1.13
    good
    0.93
     Good
    0.89
    Good
    0.88
     GOOD
    0.81
    GOOD
    0.77
     enough
    0.63
    клопе
    0.55
     gute
    0.53
     Geraadpleegd
    0.51
    Activations Density 0.015%

    No Known Activations