© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91425
    Prev
    Next
    INDEX
    Explanations

    problems

    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
     HasFactory
    -0.52
    OfYear
    -0.49
    ucine
    -0.49
    omat
    -0.47
    abestanden
    -0.47
     Mention
    -0.46
    ">$
    -0.45
     Suits
    -0.45
    urized
    -0.45
    maru
    -0.45
    POSITIVE LOGITS
    Portail
    0.60
     INTERESAR
    0.60
    XmlAccessType
    0.60
    يكب
    0.56
    endphp
    0.55
    .
    0.54
    TintMode
    0.54
    protoc
    0.54
    HideFlags
    0.52
    ArrowToggle
    0.52
    Activations Density 0.027%

    No Known Activations