© 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. 39903
    Prev
    Next
    INDEX
    Explanations

    loff

    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
    loff
    -1.17
     Leiden
    -0.81
    ossi
    -0.67
    obb
    -0.60
    AxisAlignment
    -0.58
     NSCoder
    -0.56
     समीक्षाओं
    -0.56
    وعة
    -0.54
    CodeAttribute
    -0.53
     établie
    -0.53
    POSITIVE LOGITS
    ViewImports
    0.58
    setopt
    0.56
    الإنجليزية
    0.53
    RegistryLite
    0.52
     estekak
    0.52
     MatDialog
    0.52
     Générale
    0.52
    misu
    0.51
     Comte
    0.51
     Kamil
    0.50
    Activations Density 0.210%

    No Known Activations