© 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. 5-CLT-HP
    4. 95242
    Prev
    Next
    INDEX
    Explanations

    the

    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
     AssemblyProduct
    -0.47
     Exactos
    -0.45
    acy
    -0.44
     introduction
    -0.42
    tagHelperRunner
    -0.41
    interpolate
    -0.40
     and
    -0.39
     externi
    -0.39
     traditionally
    -0.38
    addGap
    -0.38
    POSITIVE LOGITS
    󠁿
    0.77
     ostavi
    0.73
     linkovi
    0.69
    脚注の使い方
    0.69
    underlying
    0.67
     Underlying
    0.65
    */
    
    
    0.64
     underlying
    0.63
    medriver
    0.63
    Билгалдахарш
    0.61
    Activations Density 0.001%

    No Known Activations