© 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. 91668
    Prev
    Next
    INDEX
    Explanations

    Technical language and documents

    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
    urals
    -0.47
    iços
    -0.42
     scenarios
    -0.41
     postings
    -0.41
     calitate
    -0.40
     vehicles
    -0.40
    Legături
    -0.40
     réservés
    -0.39
     هایی
    -0.39
    theoremstyle
    -0.39
    POSITIVE LOGITS
    featureID
    0.80
     الحره
    0.77
    RUnlock
    0.73
     للاسماء
    0.71
    SequentialGroup
    0.67
     Италијани
    0.67
    webElement
    0.67
    లాలు
    0.66
    <bos>
    0.66
    uncher
    0.63
    Activations Density 0.079%

    No Known Activations