© 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. 42440
    Prev
    Next
    INDEX
    Explanations

    coverings

    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
     movements
    -0.74
     Movements
    -0.61
     anteriore
    -0.61
    movements
    -0.59
     movimentos
    -0.58
     výbě
    -0.58
     openings
    -0.58
     compositional
    -0.57
     madness
    -0.57
     movimientos
    -0.56
    POSITIVE LOGITS
     BorderSide
    0.59
    posedge
    0.59
    Xna
    0.58
    IGraphics
    0.56
    XDECREF
    0.55
     TextAlign
    0.54
    (!__
    0.54
    loài
    0.54
    TabStop
    0.54
    zarchiwizowane
    0.54
    Activations Density 1.483%

    No Known Activations