© 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. 1-CLT-HP
    7. 13060
    Prev
    Next
    INDEX
    Explanations

    Con

    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
    StoryboardSegue
    -0.50
     defStyleAttr
    -0.48
    Бахар
    -0.48
    SourceChecksum
    -0.44
     Melton
    -0.43
     Shawnee
    -0.41
    StreetMap
    -0.41
    WebVitals
    -0.39
    tagHelper
    -0.39
    GenerationType
    -0.39
    POSITIVE LOGITS
     ujednoznacz
    0.62
    lines
    0.60
    vos
    0.60
    }>;
    0.59
    WithIOException
    0.58
    corns
    0.57
    venido
    0.55
    obiety
    0.55
     Luci
    0.53
    ...');
    0.53
    Activations Density 0.015%

    No Known Activations