© 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. 0-CLT-HP
    7. 1204
    Prev
    Next
    INDEX
    Explanations

    procedures

    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
     procedure
    -2.39
     procedures
    -2.31
    procedure
    -2.23
    procedures
    -2.13
     Procedures
    -2.11
     Procedure
    -2.02
    Procedures
    -1.87
    Procedure
    -1.84
     PROCEDURE
    -1.84
     PROCEDURES
    -1.80
    POSITIVE LOGITS
    ist
    0.79
    ize
    0.63
    ized
    0.59
    ization
    0.55
    ists
    0.55
    ise
    0.52
    ised
    0.51
    mazione
    0.49
    izing
    0.49
    ǒ
    0.48
    Activations Density 0.221%

    No Known Activations