© 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. 92418
    Prev
    Next
    INDEX
    Explanations

    withIdentifier

    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
     CURIAM
    -0.82
    +#+#
    -0.78
     Bambi
    -0.73
    DockStyle
    -0.71
     становника
    -0.70
     سكانية
    -0.69
    __':
    -0.69
     незавершена
    -0.68
    tonsoft
    -0.68
    esModule
    -0.67
    POSITIVE LOGITS
    Revenir
    0.51
    ghar
    0.51
     Aer
    0.46
     Flare
    0.44
    kre
    0.42
    ğe
    0.42
    Aer
    0.41
    ige
    0.41
    paž
    0.41
    ]_{
    0.41
    Activations Density 0.001%

    No Known Activations