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. 1-CLT-HP
    4. 11183
    Prev
    Next
    INDEX
    Explanations

    recording information

    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
    Geplaatst
    -0.81
    Personensuche
    -0.79
    ագրություններ
    -0.79
    GEBURTSDATUM
    -0.77
     estekak
    -0.77
    hyrchwyd
    -0.75
    AndEndTag
    -0.73
     lenker
    -0.73
    MigrationBuilder
    -0.72
    MLLoader
    -0.71
    POSITIVE LOGITS
     ge
    0.47
    noscript
    0.45
     the
    0.45
     a
    0.45
    *}
    
    0.44
     localization
    0.43
     klucz
    0.43
     Percival
    0.42
     Vo
    0.42
    phyllum
    0.42
    Activations Density 0.006%

    No Known Activations