© 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. 882
    Prev
    Next
    INDEX
    Explanations

    who

    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
    Varint
    -0.73
     الحره
    -0.69
    CloseOperation
    -0.67
    })();
    -0.65
    protoimpl
    -0.65
    jbl
    -0.63
     Empieza
    -0.59
     InputDecoration
    -0.58
     Merit
    -0.58
     oprot
    -0.57
    POSITIVE LOGITS
    peur
    0.51
    posób
    0.50
    ConstraintMaker
    0.48
    jší
    0.46
     définiti
    0.46
     tapi
    0.45
    iddish
    0.45
     es
    0.44
     prefer
    0.44
     kepad
    0.43
    Activations Density 0.002%

    No Known Activations