© 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. 1-CLT-HP
    7. 9191
    Prev
    Next
    INDEX
    Explanations

    Names and legal text

    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
    nett
    -2.41
    NETT
    -1.38
     nett
    -0.66
    IVAL
    -0.55
     Barnett
    -0.53
    reuung
    -0.53
    choly
    -0.52
    URIComponent
    -0.50
     Burnett
    -0.48
    dropIfExists
    -0.48
    POSITIVE LOGITS
    fromnode
    0.66
    RegistryLite
    0.65
    ɵ
    0.57
    FormTagHelper
    0.56
     Roque
    0.56
    tır
    0.56
     ALR
    0.54
    MetaObject
    0.54
     quartzite
    0.53
     roux
    0.52
    Activations Density 0.007%

    No Known Activations