© 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. 4-CLT-HP
    7. 895
    Prev
    Next
    INDEX
    Explanations

    I

    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
    <bos>
    -0.60
     herself
    -0.45
     themselves
    -0.45
     itself
    -0.43
     connue
    -0.42
     himself
    -0.42
     sắt
    -0.39
     åt
    -0.39
    نامج
    -0.37
    themselves
    -0.37
    POSITIVE LOGITS
    httphttps
    0.84
    omiast
    0.80
     متعلقه
    0.70
    .";
    0.69
    +#+#
    0.69
    //});
    0.67
    stones
    0.67
     ”.
    0.66
    LLocation
    0.65
    flashdata
    0.65
    Activations Density 0.004%

    No Known Activations