© 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. 90958
    Prev
    Next
    INDEX
    Explanations

    gender

    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
     resourceCulture
    -1.05
    ValueStyle
    -1.00
     Female
    -0.97
    Female
    -0.96
     CreateTagHelper
    -0.95
    NameInMap
    -0.89
     للاسماء
    -0.88
     pinulongan
    -0.85
     समीक्षाओं
    -0.83
     consultato
    -0.83
    POSITIVE LOGITS
     breeder
    0.48
    Salvar
    0.41
     memberId
    0.40
    therapist
    0.40
     driver
    0.40
    قات
    0.39
     dealer
    0.39
     pitcher
    0.39
     poker
    0.38
     owner
    0.38
    Activations Density 0.116%

    No Known Activations