© 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. 90949
    Prev
    Next
    INDEX
    Explanations

    General information/news

    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
    routeProvider
    -0.57
    ThroughAttribute
    -0.51
    TemporalType
    -0.49
    WithIOException
    -0.47
    :✨
    -0.46
    AttributeSet
    -0.45
    underlying
    -0.43
    __((
    -0.43
    暫
    -0.42
    LookAnd
    -0.42
    POSITIVE LOGITS
     Monfieur
    0.80
    phazard
    0.78
     Theſe
    0.73
     itſelf
    0.71
     ainfi
    0.69
     Anſ
    0.68
     mourir
    0.68
     fevere
    0.67
     littéraire
    0.66
     Majefty
    0.66
    Activations Density 0.215%

    No Known Activations