© 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. 0-CLT-HP
    7. 38482
    Prev
    Next
    INDEX
    Explanations

    scientific research

    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
    thick
    -0.91
     thick
    -0.88
     regression
    -0.85
     Regression
    -0.84
    regression
    -0.81
    Thick
    -0.79
     Thick
    -0.75
     épais
    -0.73
    Regression
    -0.69
     doucement
    -0.62
    POSITIVE LOGITS
    i
    0.79
    ed
    0.71
    o
    0.66
    SourceChecksum
    0.61
    حياته
    0.60
    #+#
    0.60
     NUKAT
    0.58
    ]));
    0.58
    IndentedString
    0.57
    e
    0.57
    Activations Density 0.047%

    No Known Activations