© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93792
    Prev
    Next
    INDEX
    Explanations

    scientific/technical text

    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
    newBuilder
    -0.55
    WebControls
    -0.50
     com
    -0.47
    onOptions
    -0.46
    tgz
    -0.46
    bonucle
    -0.45
     SL
    -0.44
     Voyez
    -0.44
     subs
    -0.44
    UnsafeEnabled
    -0.44
    POSITIVE LOGITS
    MigrationBuilder
    0.62
    
    0.57
     للمعارف
    0.57
    })));
    0.54
    idste
    0.54
     Muse
    0.53
     MUSE
    0.52
     RACE
    0.49
     gobier
    0.49
    Programs
    0.49
    Activations Density 0.002%

    No Known Activations