© 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. 43995
    Prev
    Next
    INDEX
    Explanations

    Weight and health

    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
     war
    -0.72
     nouns
    -0.66
     Pace
    -0.64
     BoxFit
    -0.62
    iseerd
    -0.60
     wartime
    -0.60
    orianCalendar
    -0.60
    nthetic
    -0.59
    crats
    -0.59
     Arms
    -0.57
    POSITIVE LOGITS
     hashCode
    0.52
    initState
    0.47
     &___
    0.46
     followers
    0.46
     inside
    0.45
     resulting
    0.45
    حات
    0.45
     Ellos
    0.45
    Eloquent
    0.45
    libft
    0.45
    Activations Density 0.123%

    No Known Activations