© 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. 1-CLT-HP
    7. 45637
    Prev
    Next
    INDEX
    Explanations

    foundation

    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
     Foundation
    -1.09
    Foundation
    -0.87
     FOUNDATION
    -0.86
     foundation
    -0.74
     Foundations
    -0.65
    foundation
    -0.60
     foundations
    -0.53
    ant
    -0.46
    Foundations
    -0.45
     fondation
    -0.44
    POSITIVE LOGITS
    }\]
    0.79
    TypedDataSet
    0.77
     myſelf
    0.77
    ="#"><
    0.77
     Majefty
    0.73
     againſt
    0.73
     raiſ
    0.73
     Roskov
    0.70
     Efq
    0.69
     Hopf
    0.69
    Activations Density 0.014%

    No Known Activations