© 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. 5-CLT-HP
    7. 5945
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    Rüyada
    -0.90
    EndGlobalSection
    -0.64
    Personensuche
    -0.60
     &___
    -0.60
    ValueGenerated
    -0.59
    +:+
    -0.59
    AutoScaleMode
    -0.59
    ,:);
    -0.58
    NameInMap
    -0.58
     ExecuteAsync
    -0.57
    POSITIVE LOGITS
     holds
    0.82
     knows
    0.79
     works
    0.79
     was
    0.77
     looks
    0.77
     traveled
    0.76
     reached
    0.75
     travelled
    0.75
     expects
    0.75
     takes
    0.75
    Activations Density 0.000%

    No Known Activations