© 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. 0-CLT-HP
    7. 92018
    Prev
    Next
    INDEX
    Explanations

    academic/technical writing

    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
     transfieras
    -0.78
    Garantía
    -0.69
    TSS
    -0.68
    UIApplication
    -0.66
    moduleId
    -0.66
     premise
    -0.66
    KommentareTeilen
    -0.66
    sidemargin
    -0.64
    FieldDescriptor
    -0.63
    ThroughAttribute
    -0.63
    POSITIVE LOGITS
    ourke
    0.50
    ast
    0.44
    ಾರ
    0.44
     للمعارف
    0.43
    aging
    0.43
    ages
    0.42
    ex
    0.41
    guila
    0.41
    sodik
    0.41
    dropIfExists
    0.40
    Activations Density 0.040%

    No Known Activations