© 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. 1966
    Prev
    Next
    INDEX
    Explanations

    code projects

    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
     متعلقه
    -0.84
    RegressionTest
    -0.68
    tagext
    -0.66
     ModelExpression
    -0.64
    存于互联网档案馆
    -0.64
    amental
    -0.61
    ilíbrio
    -0.60
    ]();
    -0.60
     >=",
    -0.59
    multer
    -0.58
    POSITIVE LOGITS
     gels
    0.42
     person
    0.41
     anno
    0.40
     \{
    0.39
    Person
    0.37
     '['
    0.37
    Nek
    0.37
     quilt
    0.37
     sy
    0.37
     verw
    0.37
    Activations Density 0.000%

    No Known Activations