© 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. 98101
    Prev
    Next
    INDEX
    Explanations

    United

    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
    tagHelperRunner
    -0.72
     ujednoznacz
    -0.68
    UrlResolution
    -0.60
     translateY
    -0.59
    DockStyle
    -0.59
    PropertyChanging
    -0.58
    (!__
    -0.56
    Portale
    -0.56
    ).}
    -0.56
    पया
    -0.56
    POSITIVE LOGITS
    ISupport
    0.61
    ptian
    0.47
    avigation
    0.40
     terme
    0.40
    reuters
    0.40
     imprimer
    0.40
    rawQuery
    0.38
    assies
    0.38
    mint
    0.38
    kheim
    0.37
    Activations Density 0.010%

    No Known Activations