© 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. 42513
    Prev
    Next
    INDEX
    Explanations

    istic

    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
     épaules
    -1.02
     démocr
    -0.96
     colorés
    -0.91
     rempliss
    -0.89
     resourceCulture
    -0.88
     medesimo
    -0.88
     amitié
    -0.88
     énergé
    -0.87
    AutoScaleMode
    -0.85
     économiques
    -0.85
    POSITIVE LOGITS
    <bos>
    0.57
    ally
    0.53
     justice
    0.47
     purity
    0.44
     initComponents
    0.43
     kn
    0.43
     plen
    0.42
     genero
    0.42
     conciliation
    0.41
     distress
    0.41
    Activations Density 0.094%

    No Known Activations