© 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. 1-CLT-HP
    7. 8711
    Prev
    Next
    INDEX
    Explanations

    blog-like content

    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
     kasarigan
    -1.06
    NameInMap
    -1.04
    tvguidetime
    -0.95
    DockStyle
    -0.93
     <=",
    -0.87
    verwijspagina
    -0.85
    sizeCache
    -0.85
    Geplaatst
    -0.84
    Vidite
    -0.84
    ^(@)
    -0.84
    POSITIVE LOGITS
    .
    0.69
     
    0.59
    !
    0.49
    k
    0.47
    <eos>
    0.46
     I
    0.46
    '
    0.46
     in
    0.45
     and
    0.44
    -
    0.43
    Activations Density 0.154%

    No Known Activations