© 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. 0-CLT-HP
    4. 42295
    Prev
    Next
    INDEX
    Explanations

    voiced

    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
    ected
    -0.66
    Gew
    -0.52
    ArgsConstructor
    -0.51
    ißt
    -0.50
    FailureListener
    -0.50
    UI
    -0.50
     Gew
    -0.50
    +#+#
    -0.48
    iksi
    -0.48
    ection
    -0.47
    POSITIVE LOGITS
     wikipagina
    0.70
    SourceChecksum
    0.68
    =?";
    0.67
    رشف
    0.60
    )*/
    0.60
    ')));
    0.59
    INSEE
    0.58
    ://"
    0.57
    AntiForgeryToken
    0.56
     ?";
    0.56
    Activations Density 0.053%

    No Known Activations