© 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. 0-CLT-HP
    7. 42618
    Prev
    Next
    INDEX
    Explanations

    nolog

    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
    nolog
    -1.17
    otonic
    -0.94
    nologi
    -0.54
     Contrast
    -0.53
     autorytatywna
    -0.51
    nologies
    -0.51
     ErrIntOverflow
    -0.51
    
    -0.50
    äsident
    -0.50
    orteur
    -0.49
    POSITIVE LOGITS
    FromArgb
    0.57
    readString
    0.56
    rungsseite
    0.56
    ique
    0.55
    WHE
    0.51
    ((((
    0.51
     discre
    0.51
    iques
    0.50
    swe
    0.50
    downloader
    0.49
    Activations Density 0.513%

    No Known Activations