© 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. 4402
    Prev
    Next
    INDEX
    Explanations

    technical/programming context

    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
     schade
    -0.51
    pertina
    -0.50
     diagnostica
    -0.48
    itarian
    -0.48
    detek
    -0.47
     venons
    -0.47
     STREAM
    -0.46
    PIXEL
    -0.46
    umpf
    -0.45
     Jumper
    -0.45
    POSITIVE LOGITS
    لينكات
    0.77
    Autoritní
    0.76
     autorytatywna
    0.66
     transfieras
    0.65
     nahilalakip
    0.65
    Hentet
    0.62
    ⓧ
    0.62
    rungsseite
    0.60
     kasarigan
    0.58
    ++]=
    0.58
    Activations Density 0.001%

    No Known Activations