© 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. 5-CLT-HP
    7. 91226
    Prev
    Next
    INDEX
    Explanations

    drug

    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
     flor
    -0.52
    stalline
    -0.52
     trái
    -0.52
    ontal
    -0.49
    MockBean
    -0.49
    iclo
    -0.48
    ulico
    -0.47
     Tick
    -0.47
     reiz
    -0.46
     Sy
    -0.46
    POSITIVE LOGITS
     للاسماء
    0.64
    #+#
    0.50
     propOrder
    0.50
    mapStateToProps
    0.48
    abase
    0.47
    tanleria
    0.47
    หวัด
    0.46
     Reverso
    0.45
     Signalez
    0.44
     (!_
    0.44
    Activations Density 0.002%

    No Known Activations