© 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. 0-CLT-HP
    7. 94955
    Prev
    Next
    INDEX
    Explanations

    body

    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
     body
    -1.41
     Body
    -1.26
    Body
    -1.13
     BODY
    -1.09
    body
    -1.03
     bodies
    -0.93
    BODY
    -0.84
     Körper
    -0.82
     Bodies
    -0.81
     cuerpo
    -0.81
    POSITIVE LOGITS
     photolibrary
    0.72
    artifactId
    0.69
    thâu
    0.69
     Référence
    0.66
     itſelf
    0.66
    +#+#
    0.65
     doubtnut
    0.62
    loem
    0.61
    zzleHttp
    0.61
    Часть
    0.60
    Activations Density 0.087%

    No Known Activations