© 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. 76636
    Prev
    Next
    INDEX
    Explanations

    Code/parsing contexts

    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
    хьтан
    -0.77
    GEBURTS
    -0.76
     Normdatei
    -0.68
     initComponents
    -0.68
     HasFactory
    -0.68
     utafitiHapana
    -0.68
     otomatig
    -0.67
    IVEREF
    -0.66
    GEBURTSDATUM
    -0.65
    opponent
    -0.65
    POSITIVE LOGITS
    saraba
    0.46
    esgue
    0.45
    BarStyle
    0.45
    irt
    0.42
    ist
    0.42
     mẫu
    0.42
    ISR
    0.41
    herz
    0.40
     vale
    0.40
    unum
    0.40
    Activations Density 0.001%

    No Known Activations