© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 95691
    Prev
    Next
    INDEX
    Explanations

    technical documents

    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
    Negative Logits
     nahilalakip
    -0.89
    脚注の使い方
    -0.66
     ujednoznacz
    -0.65
    IonicModule
    -0.65
    Autoritní
    -0.60
    KURZBESCHREIBUNG
    -0.59
    stech
    -0.59
     BrowserModule
    -0.59
    ities
    -0.58
     ComVisible
    -0.58
    POSITIVE LOGITS
    ing
    0.63
    text
    0.52
    past
    0.52
    meal
    0.51
    lifting
    0.49
    beard
    0.48
    bridge
    0.48
    base
    0.46
     gminy
    0.46
    Detector
    0.45
    Activations Density 0.067%

    No Known Activations