© 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. 1-CLT-HP
    7. 10631
    Prev
    Next
    INDEX
    Explanations

    subject

    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
    loài
    -0.66
     Subject
    -0.59
    (',');
    -0.58
    '));
    -0.57
    "]=
    -0.57
    GIVEREF
    -0.56
    KEYCODE
    -0.55
     SqlCommand
    -0.54
    Subject
    -0.54
     jsPsych
    -0.53
    POSITIVE LOGITS
     to
    0.63
    ing
    0.61
    led
    0.60
    ttes
    0.60
    d
    0.59
    ed
    0.53
    ED
    0.53
    ar
    0.50
    es
    0.50
    клопе
    0.49
    Activations Density 0.011%

    No Known Activations