© 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. 97006
    Prev
    Next
    INDEX
    Explanations

    similarity/resemblance

    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
    aarrggbb
    -0.64
    Jeografia
    -0.56
     kasarigan
    -0.56
     Autorizaciones
    -0.50
    .*")]
    -0.50
    вгения
    -0.49
    #
    -0.49
     autorytatywna
    -0.48
    хьтан
    -0.46
    CRR
    -0.43
    POSITIVE LOGITS
     in
    0.81
     between
    0.79
    InstanceState
    0.73
     Between
    0.69
    Hozzáférés
    0.65
    ends
    0.63
     между
    0.63
    between
    0.62
     BETWEEN
    0.62
     medzi
    0.62
    Activations Density 0.002%

    No Known Activations