© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92686
    Prev
    Next
    INDEX
    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
     '
    -0.69
     "
    -0.65
     ’
    -0.61
     ‘
    -0.59
     
    -0.57
     “
    -0.57
     z
    -0.56
     `
    -0.55
    ])[
    -0.53
     that
    -0.51
    POSITIVE LOGITS
    tvguidetime
    0.80
    rungsseite
    0.80
    tagHelperRunner
    0.77
     تضيفلها
    0.74
     nakalista
    0.69
    ArrowToggle
    0.68
     autorytatywna
    0.67
    Bibliograf
    0.67
     >=",
    0.65
     disambiguazione
    0.63
    Activations Density 0.002%

    No Known Activations