© 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. 1-CLT-HP
    7. 9816
    Prev
    Next
    INDEX
    Explanations

    allows

    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
    ValueStyle
    -0.65
     precisione
    -0.61
     للمعارف
    -0.60
    iermark
    -0.55
    __*/
    -0.53
    AsUp
    -0.53
     Exacts
    -0.52
     Allí
    -0.51
     (!__
    -0.51
     CURIAM
    -0.51
    POSITIVE LOGITS
     to
    0.61
    printStackTrace
    0.58
     us
    0.52
     performing
    0.50
     for
    0.50
     not
    0.49
     replacing
    0.49
     doing
    0.47
     running
    0.46
    AZIONI
    0.45
    Activations Density 0.094%

    No Known Activations