© 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. 91813
    Prev
    Next
    INDEX
    Explanations

    or

    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
    principalColumn
    -0.67
     Jop
    -0.61
    SharedDtor
    -0.58
    enterOuterAlt
    -0.57
    VIAF
    -0.57
     Савезне
    -0.56
    crollView
    -0.56
     kasarigan
    -0.56
    httphttps
    -0.56
    IntoConstraints
    -0.54
    POSITIVE LOGITS
    med
    0.62
     فريبيس
    0.61
    ming
    0.54
    MING
    0.52
     équilibre
    0.47
    avenir
    0.47
    āng
    0.47
    micas
    0.45
    bed
    0.44
     ExecuteAsync
    0.44
    Activations Density 0.009%

    No Known Activations