© 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. 94299
    Prev
    Next
    INDEX
    Explanations

    rowth

    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
     board
    -1.13
     BOARD
    -0.76
     Board
    -0.74
     متعلقه
    -0.73
     مرئيه
    -0.67
     siège
    -0.65
    executed
    -0.63
    extended
    -0.61
    Board
    -0.60
    istar
    -0.60
    POSITIVE LOGITS
    ness
    0.73
    RenderAtEndOf
    0.66
    ScopeManager
    0.59
    ConstraintMaker
    0.53
    УДК
    0.48
    XtraEditors
    0.46
    DDG
    0.44
     ResNet
    0.43
     cfs
    0.42
     acl
    0.42
    Activations Density 0.052%

    No Known Activations