© 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. 98017
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    httphttps
    -0.51
    expandindo
    -0.46
     незавершена
    -0.46
     calendriers
    -0.45
     Marca
    -0.42
    drücke
    -0.42
    extends
    -0.42
    ');?>
    -0.42
    ']):
    -0.42
     TAMBIÉN
    -0.42
    POSITIVE LOGITS
    writeFieldEnd
    0.64
    ImageContext
    0.61
     kaynağından
    0.61
     dépens
    0.59
     Sorted
    0.57
    ntö
    0.57
    ATEGY
    0.56
     maux
    0.56
    PathVariable
    0.55
    VersionUID
    0.54
    Activations Density 0.002%

    No Known Activations