© 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. 5-CLT-HP
    7. 95054
    Prev
    Next
    INDEX
    Explanations

    in

    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
     insuffisamment
    -0.71
    )_/¯
    -0.63
    XmlAccessorType
    -0.60
    Ārējās
    -0.60
    WriteLiteral
    -0.56
     @"/
    -0.54
    whose
    -0.53
    Scénario
    -0.52
    AddTagHelper
    -0.51
    providedIn
    -0.50
    POSITIVE LOGITS
     protoimpl
    0.62
    Климат
    0.54
    cisive
    0.47
    GOTREF
    0.46
    +#+
    0.46
    ukone
    0.44
    HAND
    0.42
    STRENGTH
    0.41
    ۇ
    0.41
    setProgress
    0.41
    Activations Density 0.005%

    No Known Activations