© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10689
    Prev
    Next
    INDEX
    Explanations

    repair

    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
     nakalista
    -0.66
     nahilalakip
    -0.61
    <bos>
    -0.60
    ragamo
    -0.60
    ształ
    -0.58
     يتيمه
    -0.57
     banget
    -0.57
    styleType
    -0.57
     amelyek
    -0.57
     repair
    -0.56
    POSITIVE LOGITS
     onCancelled
    0.59
    OrNil
    0.58
    SuccessListener
    0.57
    ers
    0.56
    er
    0.52
    oprecip
    0.49
    erci
    0.48
    PrototypeOf
    0.47
    providedIn
    0.46
    principalTable
    0.46
    Activations Density 0.023%

    No Known Activations