© 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. 5-CLT-HP
    7. 94333
    Prev
    Next
    INDEX
    Explanations

    influence

    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
    AndroidJUnit
    -0.72
    Autoritní
    -0.68
    ArgsConstructor
    -0.66
    */;
    -0.62
    TypedDataSet
    -0.60
    NOPQRST
    -0.60
    %");
    -0.60
    RuleContext
    -0.59
    NUMX
    -0.58
    ensement
    -0.58
    POSITIVE LOGITS
     change
    0.69
     events
    0.56
     changes
    0.55
    change
    0.54
     CHANGE
    0.51
     important
    0.49
     outcomes
    0.49
    hasMoreElements
    0.49
     cambio
    0.48
    ributions
    0.47
    Activations Density 0.007%

    No Known Activations