Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 1258
    Prev
    Next
    INDEX
    Explanations

    research papers

    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
     dAtA
    -0.59
     maksud
    -0.58
    \{\\
    -0.57
     esfuer
    -0.52
     ModelExpression
    -0.52
    breos
    -0.52
     tarko
    -0.51
    akor
    -0.49
    Климат
    -0.49
    rrggbb
    -0.49
    POSITIVE LOGITS
    adalah
    0.60
     AssemblyTitle
    0.57
     lack
    0.57
     realizing
    0.54
     realising
    0.53
    DispatchToProps
    0.53
    قایناقلار
    0.53
     death
    0.52
     overcoming
    0.51
    lanması
    0.50
    Activations Density 0.003%

    No Known Activations