© 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. 94375
    Prev
    Next
    INDEX
    Explanations

    silicon, electronics

    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
     Knows
    -0.73
     knows
    -0.51
    arta
    -0.50
     entweder
    -0.47
    knows
    -0.47
     circunstancia
    -0.47
    وره
    -0.46
     end
    -0.45
    hommes
    -0.45
     */;
    -0.45
    POSITIVE LOGITS
    AndroidJUnit
    0.88
     оригіналу
    0.82
    ThroughAttribute
    0.76
     TextAppearance
    0.73
    titleMargin
    0.73
     بيها
    0.73
    >{@
    0.69
    Vidite
    0.69
    AndEndTag
    0.69
    WithIOException
    0.68
    Activations Density 0.191%

    No Known Activations