© 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. 45764
    Prev
    Next
    INDEX
    Explanations

    data

    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
    arna
    -0.46
     hashlib
    -0.45
    er
    -0.44
    bad
    -0.44
     qua
    -0.43
    ar
    -0.41
    aux
    -0.41
    ap
    -0.41
     var
    -0.41
    var
    -0.40
    POSITIVE LOGITS
    CppMethod
    0.91
     كومونز
    0.87
    évaluateur
    0.74
     AssemblyCulture
    0.71
    IntoConstraints
    0.71
    richTextPanel
    0.69
     muualla
    0.69
    AddTagHelper
    0.68
     ostavi
    0.68
     CWE
    0.66
    Activations Density 0.006%

    No Known Activations