Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73955
    Prev
    Next
    INDEX
    Explanations

    code and file paths

    np_max-act-logits · 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
    :✨
    -0.74
     >=",
    -0.61
     sinner
    -0.57
    Distribuzione
    -0.55
     courtes
    -0.54
    Belo
    -0.54
    Abit
    -0.54
     unwra
    -0.52
     foreign
    -0.52
    WebGL
    -0.52
    POSITIVE LOGITS
    ponses
    0.47
    tvguidetime
    0.44
    twimg
    0.42
     Biôgrafia
    0.40
     Référence
    0.40
     Rado
    0.40
    toThrow
    0.40
    Становништво
    0.40
     AttributeSet
    0.40
    LookAnd
    0.39
    Activations Density 0.006%

    No Known Activations