© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 15482
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    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
     separately
    -0.58
     same
    -0.57
    tec
    -0.52
    cad
    -0.50
     far
    -0.50
     co
    -0.50
    cre
    -0.50
     similarly
    -0.49
     pu
    -0.48
     True
    -0.48
    POSITIVE LOGITS
    <bos>
    1.69
     étoient
    0.93
     avoient
    0.93
     aveug
    0.92
     vectorielles
    0.91
    CloseOperation
    0.87
     présidenti
    0.87
     prisonniers
    0.86
     mères
    0.86
     trasmissione
    0.86
    Activations Density 0.002%

    No Known Activations