© 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. 42771
    Prev
    Next
    INDEX
    Explanations

    around

    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
    IntoConstraints
    -0.78
    Rüyada
    -0.69
    WebServlet
    -0.67
     ordf
    -0.63
    colgroup
    -0.60
    SerializedName
    -0.59
     Everybody
    -0.54
     guy
    -0.53
     Surround
    -0.53
     inflows
    -0.53
    POSITIVE LOGITS
    ."));
    0.57
    )];
    0.54
    .";
    0.53
    [];
    0.49
    }());
    0.48
    StoryboardSegue
    0.48
     endwhile
    0.48
       
    0.48
    endwhile
    0.48
    iul
    0.47
    Activations Density 0.111%

    No Known Activations