© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13351
    Prev
    Next
    INDEX
    Explanations

    to

    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
    principalTable
    -0.73
     nahilalakip
    -0.66
    IsContent
    -0.66
     mourut
    -0.66
    +#+#
    -0.65
    expandindo
    -0.65
    windowFixed
    -0.65
     was
    -0.63
    AccessorTable
    -0.61
     were
    -0.61
    POSITIVE LOGITS
     escalate
    0.70
     arise
    0.65
     arrive
    0.61
     emerge
    0.60
     invade
    0.56
     acquire
    0.56
     introduce
    0.56
     fail
    0.55
     write
    0.55
     become
    0.55
    Activations Density 0.164%

    No Known Activations