© 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. 1-CLT-HP
    7. 10425
    Prev
    Next
    INDEX
    Explanations

    code

    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
     للمعارف
    -0.61
    torio
    -0.58
     Wikimedijinoj
    -0.56
    copg
    -0.55
    rogly
    -0.54
    __':
    -0.52
    таратура
    -0.51
    ########.
    -0.50
    LookAnd
    -0.48
     contrasting
    -0.48
    POSITIVE LOGITS
     MonoBehaviour
    0.63
    bindParam
    0.57
    
    0.57
    HideInInspector
    0.57
    addPreferredGap
    0.56
     oreilles
    0.54
     bienfaits
    0.54
    cjonal
    0.53
     Plantation
    0.53
    nesia
    0.53
    Activations Density 0.699%

    No Known Activations