© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 38899
    Prev
    Next
    INDEX
    Explanations

    code/math

    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
    Diweddarwch
    -1.05
    providedIn
    -1.02
    OGND
    -0.94
    ScopeManager
    -0.86
    parsedMessage
    -0.85
    featureID
    -0.83
    ArgsConstructor
    -0.83
     defaultstate
    -0.81
    SourceChecksum
    -0.81
    rungsseite
    -0.80
    POSITIVE LOGITS
     of
    0.54
     tepat
    0.48
     as
    0.47
    كت
    0.47
     matrimon
    0.46
    vad
    0.45
    ↵
    0.44
     common
    0.42
    ↵↵
    0.41
    Common
    0.40
    Activations Density 1.814%

    No Known Activations