© 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. 74714
    Prev
    Next
    INDEX
    Explanations

    Red colors

    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
    mybatisplus
    -0.74
    awtextra
    -0.68
     wireType
    -0.67
    NamedQueries
    -0.65
     HttpNotFound
    -0.60
    addContainerGap
    -0.57
     дописавши
    -0.56
    ykjav
    -0.53
    رایط
    -0.52
     @"/
    -0.52
    POSITIVE LOGITS
     cherry
    0.68
     blood
    0.59
     Cherry
    0.58
    cherry
    0.52
    coca
    0.51
    cob
    0.51
     BLOOD
    0.50
     a
    0.49
     jet
    0.49
     beetroot
    0.48
    Activations Density 0.000%

    No Known Activations