© 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. 4-CLT-HP
    7. 966
    Prev
    Next
    INDEX
    Explanations

    that

    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
     ModelExpression
    -0.76
     mówią
    -0.74
    zają
    -0.69
     Were
    -0.60
    arise
    -0.59
    Were
    -0.57
    uggest
    -0.56
     appel
    -0.55
    HAVE
    -0.55
     accompany
    -0.54
    POSITIVE LOGITS
    <bos>
    1.00
     offers
    0.66
     uses
    0.66
     focuses
    0.64
     continues
    0.64
     was
    0.61
     functions
    0.61
     has
    0.61
     acts
    0.59
     takes
    0.58
    Activations Density 0.034%

    No Known Activations