© 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. 95609
    Prev
    Next
    INDEX
    Explanations

    s

    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
     or
    -0.49
     in
    -0.49
     on
    -0.47
     do
    -0.46
     does
    -0.46
     generates
    -0.45
     contains
    -0.45
     came
    -0.44
     دارد
    -0.44
     provides
    -0.44
    POSITIVE LOGITS
    InjectAttribute
    1.04
     referenties
    0.81
    NewUrlParser
    0.81
     فريبيس
    0.80
     صوتيه
    0.80
     ligiloj
    0.79
    ſelves
    0.77
    ArgsConstructor
    0.75
     Signalez
    0.75
     kasarigan
    0.73
    Activations Density 0.121%

    No Known Activations