© 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. 9622
    Prev
    Next
    INDEX
    Explanations

    after

    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
     jsonify
    -0.55
    BackStack
    -0.53
     onPostExecute
    -0.52
     Boltzmann
    -0.51
    HomeAsUpEnabled
    -0.50
     LUMI
    -0.50
     TextAlign
    -0.49
     CURIAM
    -0.49
    يميديا
    -0.48
    =$?
    -0.48
    POSITIVE LOGITS
    SerializedSize
    0.60
    enterOuterAlt
    0.60
    FFER
    0.51
     Invitation
    0.50
    haviour
    0.50
    peria
    0.50
     Vorsch
    0.49
    Alike
    0.48
     ذ
    0.48
     lyd
    0.48
    Activations Density 0.065%

    No Known Activations