© 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. 97967
    Prev
    Next
    INDEX
    Explanations

    ing

    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
    Autoritní
    -0.78
     a
    -0.72
     the
    -0.63
     an
    -0.59
    MANN
    -0.57
    áctenos
    -0.56
     his
    -0.56
    YARD
    -0.52
    reya
    -0.52
     comp
    -0.51
    POSITIVE LOGITS
     of
    1.37
    KommentareTeilen
    0.75
    sidemargin
    0.67
    出版年
    0.67
    tagHelperRunner
    0.65
     يتيمه
    0.64
     whereof
    0.62
     privés
    0.60
     privée
    0.60
     autorisés
    0.59
    Activations Density 0.006%

    No Known Activations