© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 91931
    Prev
    Next
    INDEX
    Explanations

    Instructions/explanations

    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
    <bos>
    -1.34
    SourceChecksum
    -0.67
    '
    -0.66
     '\\;'
    -0.57
    LookAnd
    -0.54
     canst
    -0.53
    /**
    -0.52
    //
    -0.52
    はじめに
    -0.51
    ↵↵
    -0.50
    POSITIVE LOGITS
     us
    0.83
     itself
    0.61
     versa
    0.58
    BeginInit
    0.58
    ícil
    0.57
     alike
    0.52
    MENAFN
    0.52
     snippetHide
    0.51
    HasAnnotation
    0.50
     cetera
    0.50
    Activations Density 0.083%

    No Known Activations