© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 97412
    Prev
    Next
    INDEX
    Explanations

    consent/agreement

    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
     assent
    -1.12
     approval
    -1.01
     consent
    -0.99
    approval
    -0.97
    consent
    -0.85
    agreement
    -0.83
     rejection
    -0.82
     disapproval
    -0.82
     APPROVAL
    -0.79
     refusal
    -0.77
    POSITIVE LOGITS
    RenderAtEndOf
    0.95
    LookAnd
    0.91
     autorytatywna
    0.74
    AddTagHelper
    0.68
    AndEndTag
    0.63
    ArgsConstructor
    0.61
    providedIn
    0.61
    Manbalar
    0.57
    yntaxException
    0.56
    IBOutlet
    0.55
    Activations Density 0.061%

    No Known Activations