© 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. 0-CLT-HP
    7. 40045
    Prev
    Next
    INDEX
    Explanations

    evaluation

    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
     appraisal
    -1.68
     evaluation
    -1.55
     Appraisal
    -1.52
     Evaluation
    -1.36
    Evaluation
    -1.33
     EVALUATION
    -1.33
     appraisals
    -1.31
    evaluation
    -1.29
     evaluations
    -1.27
     appraise
    -1.23
    POSITIVE LOGITS
    tagHelperRunner
    0.61
    Diweddarwch
    0.59
     of
    0.51
     beginnetje
    0.50
    chartInstance
    0.46
     '{@
    0.46
    emble
    0.45
    AnchorTagHelper
    0.45
    TypedDataSet
    0.45
    jsxFileName
    0.45
    Activations Density 0.124%

    No Known Activations