© 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. 5-CLT-HP
    7. 92627
    Prev
    Next
    INDEX
    Explanations

    code and data files

    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
    ⓧ
    -0.60
     Lucca
    -0.58
     Tratado
    -0.56
     Linked
    -0.54
    OMA
    -0.54
    folio
    -0.53
     svolge
    -0.51
     tig
    -0.49
     Maior
    -0.49
     Continuous
    -0.49
    POSITIVE LOGITS
     autorytatywna
    0.91
    évaluateur
    0.70
    LookAnd
    0.66
    зулта
    0.64
    ConstraintMaker
    0.63
     CreateTagHelper
    0.63
     дописавши
    0.62
    IUrlHelper
    0.61
    AutoField
    0.60
    elemField
    0.59
    Activations Density 0.002%

    No Known Activations