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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 15678
    Prev
    Next
    INDEX
    Explanations

    code

    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
     code
    -0.98
     Codes
    -0.96
    codes
    -0.95
    code
    -0.94
     codes
    -0.94
    Code
    -0.93
     Code
    -0.90
    CODE
    -0.90
     getCode
    -0.87
     تضيفلها
    -0.85
    POSITIVE LOGITS
    ⓘ
    0.49
    VIAF
    0.49
     OMITBAD
    0.45
     VizieR
    0.44
     Trapp
    0.43
    ÊN
    0.40
     invited
    0.40
     VIAF
    0.39
    UnknownFields
    0.39
     loafers
    0.39
    Activations Density 0.238%

    No Known Activations