© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41762
    Prev
    Next
    INDEX
    Explanations

    Loopholes and methods

    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
    teps
    -0.68
    tep
    -0.63
    ThroughAttribute
    -0.53
    FailureListener
    -0.51
    picasso
    -0.50
     posses
    -0.49
    BOUND
    -0.48
    GraphicsUnit
    -0.47
    bead
    -0.47
    sendRedirect
    -0.47
    POSITIVE LOGITS
    NameInMap
    0.95
    +#+#
    0.78
    Portale
    0.69
     дописавши
    0.69
    itev
    0.60
    OGND
    0.58
    Портал
    0.57
    ed
    0.57
    GeoNames
    0.57
    mények
    0.56
    Activations Density 0.087%

    No Known Activations