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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97444
    Prev
    Next
    INDEX
    Explanations

    refusal and consent and negation

    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
    XtraEditors
    -0.59
    AnimationsModule
    -0.57
     invokingState
    -0.52
    ObjectContext
    -0.50
    SqlConnection
    -0.49
    kwds
    -0.47
    WebElementEntity
    -0.46
    SourceChecksum
    -0.46
    tadiene
    -0.45
    letzt
    -0.44
    POSITIVE LOGITS
     appropriately
    0.65
     frumos
    0.61
     requests
    0.61
     tartalomajánló
    0.59
     properly
    0.59
     Requests
    0.55
     wikihow
    0.54
     APPROPRI
    0.54
     nicely
    0.54
     للمعارف
    0.54
    Activations Density 0.000%

    No Known Activations