© 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. 0-CLT-HP
    7. 94758
    Prev
    Next
    INDEX
    Explanations

    single quotes

    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
    ‘
    -1.88
    “
    -1.66
    «
    -0.96
    “…
    -0.89
    „
    -0.89
    “,
    -0.88
    “.
    -0.84
     ‘
    -0.82
     “
    -0.80
    「
    -0.78
    POSITIVE LOGITS
    ^(@)
    1.08
    NUMX
    0.96
    !")
    0.94
    .";
    0.94
    ſelf
    0.86
     $_"
    0.85
    $.
    0.85
    )");
    0.85
    
    0.84
    %");
    0.83
    Activations Density 0.734%

    No Known Activations