© 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. 4-CLT-HP
    7. 1032
    Prev
    Next
    INDEX
    Explanations

    right

    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
    aarrggbb
    -0.82
    StoryboardSegue
    -0.78
    клопе
    -0.77
    Personensuche
    -0.77
    ^(@)
    -0.71
    Portale
    -0.71
    ]")]
    -0.70
    ViewInit
    -0.70
     незавершена
    -0.68
    WebVitals
    -0.67
    POSITIVE LOGITS
     into
    0.68
     in
    0.63
     Into
    0.62
    way
    0.59
     before
    0.54
    Into
    0.54
     above
    0.53
    where
    0.51
    into
    0.50
     where
    0.50
    Activations Density 0.012%

    No Known Activations