© 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. 20-CLT-HP
    7. 72215
    Prev
    Next
    INDEX
    Explanations

    cross

    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
     صوتيه
    -0.73
    UnusedPrivate
    -0.57
     Seeder
    -0.52
     Eisenhower
    -0.51
     placement
    -0.50
    лтемелер
    -0.49
     Regional
    -0.48
     CreateTagHelper
    -0.48
     Marian
    -0.48
     Marin
    -0.47
    POSITIVE LOGITS
     GoogleFonts
    0.58
     layui
    0.53
    lingu
    0.53
    parsedMessage
    0.53
    ]--;
    0.53
     tæn
    0.53
    GEBURTSDATUM
    0.48
     gare
    0.48
    Климат
    0.48
    pleft
    0.47
    Activations Density 0.005%

    No Known Activations