© 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. 4436
    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
     however
    -0.75
     accordingly
    -0.69
    However
    -0.68
     However
    -0.68
     ويكيپيديا
    -0.64
    .
    -0.62
     trotzdem
    -0.61
    however
    -0.59
     ब्रेकडाउन
    -0.58
     wireType
    -0.58
    POSITIVE LOGITS
    хьтан
    0.63
    いただき
    0.57
    featureID
    0.57
    ,‎
    0.54
    Geplaatst
    0.54
    ,
    0.52
     והוא
    0.51
    ,}
    0.49
     [],
    0.48
    GTCX
    0.48
    Activations Density 0.002%

    No Known Activations