© 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. 5-CLT-HP
    7. 96217
    Prev
    Next
    INDEX
    Explanations

    technical writing

    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
     myſelf
    -0.86
     itſelf
    -0.82
     Monfieur
    -0.77
     Efq
    -0.72
     auffi
    -0.72
     purpoſe
    -0.71
     againſt
    -0.69
     ſta
    -0.68
     Majefty
    -0.68
     raiſ
    -0.67
    POSITIVE LOGITS
    TabIndex
    0.53
    readAs
    0.52
    onde
    0.50
    jsii
    0.50
    ()][
    0.47
    empt
    0.47
    AndEndTag
    0.47
    gonic
    0.47
    Pod
    0.46
    grunt
    0.46
    Activations Density 0.014%

    No Known Activations