© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 95202
    Prev
    Next
    INDEX
    Explanations

    from

    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
     avocados
    -0.55
     neutrinos
    -0.53
    oredCriteria
    -0.51
     dignité
    -0.50
     Shaksp
    -0.50
    uxxxx
    -0.50
     Colombie
    -0.50
     marshmallows
    -0.50
     and
    -0.49
     mortars
    -0.49
    POSITIVE LOGITS
    TagMode
    0.63
    期刊论文
    0.57
    usercontent
    0.56
     StatelessWidget
    0.54
    Tracce
    0.52
    Reilly
    0.52
     ExecuteAsync
    0.51
    userdetails
    0.51
     VIAF
    0.51
    _;
    0.51
    Activations Density 0.001%

    No Known Activations