© 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. 0-CLT-HP
    7. 94730
    Prev
    Next
    INDEX
    Explanations

    +="@+"

    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
    rillo
    -0.52
    ="";
    -0.48
    multirow
    -0.48
     "/";
    -0.47
    ="";
    -0.47
    “
    -0.47
    卒業
    -0.45
     Holm
    -0.45
    اهم
    -0.45
     Gardner
    -0.44
    POSITIVE LOGITS
    HasForeignKey
    0.75
    EndContext
    0.73
     viewType
    0.73
    PreferredItem
    0.69
     nawr
    0.69
     AspNetCore
    0.68
     Réponses
    0.67
    onAttach
    0.67
    ⏟
    0.67
    ГЛА
    0.66
    Activations Density 0.164%

    No Known Activations