© 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. 0-CLT-HP
    7. 45241
    Prev
    Next
    INDEX
    Explanations

    ²

    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
    ulman
    -0.91
    ²
    -0.87
    hearted
    -0.71
    ly
    -0.56
    lessly
    -0.54
    heartedly
    -0.54
    2
    -0.53
    ATELY
    -0.52
    multicolumn
    -0.51
    tvrt
    -0.51
    POSITIVE LOGITS
    <?
    0.77
    RenderAtEndOf
    0.76
     MainAxisSize
    0.70
    ValueStyle
    0.65
     дописавши
    0.63
    MENAFN
    0.63
     wikipagina
    0.62
     ChromeDriver
    0.62
    CodeAttribute
    0.62
     bezeichneter
    0.62
    Activations Density 0.036%

    No Known Activations