© 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. 5187
    Prev
    Next
    INDEX
    Explanations

    appearance/showing up

    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
     to
    -0.77
     Мексичка
    -0.56
    DataTo
    -0.49
    tées
    -0.47
    rativa
    -0.47
     כפ
    -0.45
    shutil
    -0.44
    折
    -0.43
     beneficial
    -0.43
    paddingVertical
    -0.43
    POSITIVE LOGITS
     on
    0.76
    AccessorTable
    0.71
    EndContext
    0.68
    ScopeManager
    0.68
     everywhere
    0.66
    everywhere
    0.63
    +#+#
    0.56
    
    0.54
     announcing
    0.54
     LEYENDO
    0.54
    Activations Density 0.002%

    No Known Activations