© 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. 4-CLT-HP
    7. 3360
    Prev
    Next
    INDEX
    Explanations

    period

    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
    <bos>
    -1.22
    contentLoaded
    -0.93
    رشف
    -0.88
    bootstrapcdn
    -0.85
    AndEndTag
    -0.85
    ⓧ
    -0.83
     мәкал
    -0.83
     виправивши
    -0.82
    ViewImports
    -0.80
    styleable
    -0.80
    POSITIVE LOGITS
     aceste
    0.41
     religieuses
    0.36
     faveur
    0.36
     berdua
    0.35
     betrekking
    0.35
    AutoresizingMask
    0.35
     būtų
    0.35
    vivencia
    0.34
     deres
    0.34
    gangss
    0.34
    Activations Density 0.221%

    No Known Activations