© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2820
    Prev
    Next
    INDEX
    Explanations

    questionnaire

    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
    
    -0.66
    ThroughAttribute
    -0.65
    BagConstraints
    -0.63
    jooq
    -0.60
     BoxFit
    -0.60
    ClientSize
    -0.56
     initComponents
    -0.54
    isela
    -0.53
    endpush
    -0.50
     NgModule
    -0.50
    POSITIVE LOGITS
     reporting
    0.54
    onaceous
    0.52
    abestanden
    0.51
    expandindo
    0.50
     about
    0.50
    @@@@@
    0.50
    rália
    0.49
    parsedMessage
    0.49
    hilangan
    0.49
    aternion
    0.47
    Activations Density 0.005%

    No Known Activations