© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 2138
    Prev
    Next
    INDEX
    Explanations

    in

    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
    ConstraintMaker
    -0.79
    ंदीखरीदारी
    -0.63
     تضيفلها
    -0.61
    msgTypes
    -0.60
    Personensuche
    -0.58
    ướ
    -0.56
    bewerken
    -0.56
    PickerController
    -0.53
    //</
    -0.53
    }")
    
    -0.52
    POSITIVE LOGITS
     stället
    0.68
     nakalista
    0.68
    berdayakan
    0.63
    WriteLiteral
    0.56
    रीदारी
    0.56
     réponse
    0.53
     tillegg
    0.53
     médias
    0.52
     coupable
    0.51
    طرز
    0.51
    Activations Density 0.000%

    No Known Activations