© 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
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 77388
    Prev
    Next
    INDEX
    Explanations

    Android code

    np_max-act-logits · 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
    oa̍t
    -0.63
    ]));
    
    -0.63
    StoryboardSegue
    -0.60
    }],
    
    -0.56
    ']));
    -0.53
    )]);
    -0.52
    ])){
    -0.52
    tela
    -0.52
     Darum
    -0.52
    ')";
    -0.50
    POSITIVE LOGITS
     CURIAM
    0.64
    adpleegd
    0.58
    
    0.55
    TintMode
    0.53
    MessageTagHelper
    0.52
    azgo
    0.51
    WEBPACK
    0.50
     становника
    0.50
    bootstrapcdn
    0.48
     مرئيه
    0.48
    Activations Density 0.000%

    No Known Activations