© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 12184
    Prev
    Next
    INDEX
    Explanations

    diseases

    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
     autorytatywna
    -0.68
    ArgsConstructor
    -0.64
    archiviato
    -0.60
     tropics
    -0.57
    DebuggerNonUser
    -0.56
     referenties
    -0.56
     Efq
    -0.56
    ItemBackground
    -0.55
     Era
    -0.55
    ">—
    -0.53
    POSITIVE LOGITS
    الحياه
    0.59
    chkin
    0.52
     Einwilligung
    0.52
    MENAFN
    0.52
    ffles
    0.50
    teva
    0.49
     EconPapers
    0.49
    chini
    0.49
    '=
    0.48
    unhofer
    0.47
    Activations Density 0.026%

    No Known Activations