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. 74324
    Prev
    Next
    INDEX
    Explanations

    code and dates

    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
    GraphicsUnit
    -0.74
     noqa
    -0.71
     ErrIntOverflow
    -0.68
    Personensuche
    -0.68
    Portály
    -0.67
     gyhoeddwyd
    -0.67
     ISNI
    -0.66
    getMenuInflater
    -0.66
     nakalista
    -0.64
    sidemargin
    -0.64
    POSITIVE LOGITS
    ın
    0.49
     deber
    0.48
     chim
    0.45
     Failure
    0.44
    streifen
    0.44
    Failure
    0.42
    idak
    0.42
    wijl
    0.42
     Breach
    0.41
     pove
    0.41
    Activations Density 0.002%

    No Known Activations