© 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. 4363
    Prev
    Next
    INDEX
    Explanations

    commas and percentages

    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
    __(/*!
    -0.57
    olella
    -0.56
    setPreferred
    -0.49
    avimo
    -0.49
    netto
    -0.47
     two
    -0.47
    NING
    -0.46
     Viss
    -0.45
    cker
    -0.45
    parel
    -0.45
    POSITIVE LOGITS
    ViewFeatures
    0.82
    HtmlAttribute
    0.71
    Tikang
    0.57
    XmlAccessType
    0.57
    niająca
    0.57
    ともに
    0.57
    VersionUID
    0.56
    共に
    0.55
     législation
    0.54
    HasForeignKey
    0.53
    Activations Density 0.024%

    No Known Activations