© 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. 1-CLT-HP
    7. 9498
    Prev
    Next
    INDEX
    Explanations

    grow

    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
    AnchorTagHelper
    -0.64
    SPATH
    -0.56
    principalTable
    -0.54
    Portale
    -0.54
     <<<<<<<<<<<<<<
    -0.53
     >=",
    -0.52
    Cage
    -0.51
     (^
    -0.50
     ModelExpression
    -0.50
    ulement
    -0.50
    POSITIVE LOGITS
     riusc
    0.51
    مصادر
    0.48
    DockStyle
    0.47
    IUrlHelper
    0.45
     مرور
    0.43
    StoreMessageInfo
    0.43
    DECREF
    0.43
    EndInit
    0.42
    UARY
    0.42
     tule
    0.42
    Activations Density 0.093%

    No Known Activations