© 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. 97554
    Prev
    Next
    INDEX
    Explanations

    ocor

    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
    OGND
    -0.84
    rungsseite
    -0.79
     igång
    -0.70
    tagHelperRunner
    -0.67
     åt
    -0.66
    e
    -0.64
     quelcon
    -0.63
    InjectAttribute
    -0.61
     étoient
    -0.60
     produisons
    -0.58
    POSITIVE LOGITS
    Hozzáférés
    0.57
    出版年
    0.54
    Viitteet
    0.52
    __).
    0.51
    goto
    0.50
    InjectMocks
    0.49
    LookAndFeel
    0.46
    DispatchToProps
    0.46
    endphp
    0.45
     незавершена
    0.45
    Activations Density 1.167%

    No Known Activations