© 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. 5-CLT-HP
    7. 91741
    Prev
    Next
    INDEX
    Explanations

    many

    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
    رشف
    -0.72
    yntaxException
    -0.68
    таратура
    -0.67
     particulières
    -0.66
    alnız
    -0.65
     especiais
    -0.65
     spéciaux
    -0.64
     réguli
    -0.64
     виправивши
    -0.63
     jsPsych
    -0.63
    POSITIVE LOGITS
     a
    0.63
     an
    0.52
     modern
    0.45
    lasher
    0.44
    EndInit
    0.43
     three
    0.42
    contentLoaded
    0.41
    ẢN
    0.41
     onCreateView
    0.40
    ẫn
    0.40
    Activations Density 0.001%

    No Known Activations