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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 407
    Prev
    Next
    INDEX
    Explanations

    computer code/math expressions

    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
    +#+#
    -0.73
     kaarangay
    -0.73
     estekak
    -0.68
    ConstraintMaker
    -0.64
    webElementXpaths
    -0.63
    ]")]
    -0.63
    сылкі
    -0.61
    PerformLayout
    -0.58
    DoubleQuotes
    -0.57
    RenderAtEndOf
    -0.57
    POSITIVE LOGITS
     Supreme
    0.63
    ctin
    0.60
    osa
    0.58
     Un
    0.54
    Supreme
    0.51
     SUPREME
    0.48
     at
    0.48
    つま
    0.47
    +:+
    0.47
    <bos>
    0.46
    Activations Density 0.000%

    No Known Activations