© 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. 77144
    Prev
    Next
    INDEX
    Explanations

    illustrated

    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
    цездатний
    -0.77
    hôte
    -0.68
     الحره
    -0.67
    paksa
    -0.67
     onAnimation
    -0.65
    ativistic
    -0.64
     SDLK
    -0.63
    colgroup
    -0.63
    URLException
    -0.61
     appelez
    -0.60
    POSITIVE LOGITS
     set
    0.52
     Set
    0.50
     over
    0.49
    Życiorys
    0.45
    Set
    0.44
     opposite
    0.42
     per
    0.41
     Normdatei
    0.39
     منها
    0.38
     SET
    0.37
    Activations Density 0.003%

    No Known Activations