© 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. 3717
    Prev
    Next
    INDEX
    Explanations

    var

    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
     tartalomajánló
    -0.63
    клопе
    -0.60
    findpost
    -0.56
     незавершена
    -0.54
    脚注の使い方
    -0.52
    illoma
    -0.52
     Matri
    -0.52
    ">:
    -0.51
    Varint
    -0.51
    Bronnen
    -0.50
    POSITIVE LOGITS
    Дереккөздер
    0.66
     saturated
    0.55
    ">//
    0.54
    URATION
    0.54
    iyor
    0.53
    preventDefault
    0.53
    věr
    0.52
    MENAFN
    0.52
    passen
    0.52
    ContextHolder
    0.52
    Activations Density 0.008%

    No Known Activations