© 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. 20-CLT-HP
    7. 74576
    Prev
    Next
    INDEX
    Explanations

    Receptors and immune system

    np_max-act-logits · 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
     صوتيه
    -0.53
    ViewImports
    -0.53
     Daz
    -0.50
     ujednoznacz
    -0.50
     yii
    -0.49
    })*/
    -0.49
     continúas
    -0.48
     husbands
    -0.48
     JSP
    -0.48
     CRS
    -0.47
    POSITIVE LOGITS
     ModelExpression
    0.57
     Ause
    0.55
    ftagPool
    0.53
    UnsafeEnabled
    0.51
    Билгалдахарш
    0.51
    FieldOffset
    0.51
    óság
    0.50
     pinulongan
    0.50
    MLLoader
    0.50
    ίδι
    0.49
    Activations Density 0.006%

    No Known Activations