© 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. 4-CLT-HP
    7. 3529
    Prev
    Next
    INDEX
    Explanations

    definitions using "to be"

    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
    chufe
    -0.69
    "},
    -0.61
    essentiel
    -0.60
     vagues
    -0.58
    beste
    -0.58
     ſame
    -0.58
     beſt
    -0.57
    },{
    -0.56
    )‏
    -0.56
    engagent
    -0.55
    POSITIVE LOGITS
     probably
    0.99
    probably
    0.89
     Probably
    0.84
     الاطلاع
    0.81
    Probably
    0.81
     perhaps
    0.76
     undoubtedly
    0.76
    presumably
    0.73
     presumably
    0.72
    perhaps
    0.71
    Activations Density 0.004%

    No Known Activations