© 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. 4-CLT-HP
    7. 4369
    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
     
    -0.52
     first
    -0.49
    1
    -0.49
     other
    -0.49
    other
    -0.49
    ana
    -0.48
    بوع
    -0.47
    _
    -0.46
     else
    -0.45
     largos
    -0.43
    POSITIVE LOGITS
     Exactos
    0.81
     purpoſe
    0.79
    DIPSETTING
    0.76
    <()>
    0.76
     Monfieur
    0.75
     Reſ
    0.73
     ་་
    0.72
    ſelves
    0.72
     pleaſure
    0.72
     itſelf
    0.71
    Activations Density 0.003%

    No Known Activations