© 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. 97220
    Prev
    Next
    INDEX
    Explanations

    findings

    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
     مرئيه
    -0.65
    XmlAccessType
    -0.60
    DockStyle
    -0.57
     tartalomajánló
    -0.56
     Wikiseite
    -0.54
    usammen
    -0.53
    berdayakan
    -0.53
    MOQ
    -0.53
     puissiez
    -0.53
    eait
    -0.53
    POSITIVE LOGITS
     these
    0.79
     many
    0.72
     countless
    0.72
     numerous
    0.70
    .
    0.67
    !
    0.66
     widely
    0.65
     variously
    0.63
     differently
    0.63
     all
    0.62
    Activations Density 0.017%

    No Known Activations