© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92973
    Prev
    Next
    INDEX
    Explanations

    resulting

    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
     resulting
    -1.00
    resulting
    -0.78
    )");
    -0.67
     ''
    -0.61
     corresponding
    -0.60
     "");
    -0.59
     ""
    -0.56
    )";
    -0.56
     résult
    -0.56
     auft
    -0.55
    POSITIVE LOGITS
    yntaxException
    0.77
    +#+#
    0.77
     propOrder
    0.76
    StoryboardSegue
    0.75
    RenderAtEndOf
    0.75
    CloseOperation
    0.69
    AutoScaleMode
    0.68
     Normdatei
    0.66
     MotionEvent
    0.64
    AndEndTag
    0.63
    Activations Density 1.396%

    No Known Activations