© 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. 91071
    Prev
    Next
    INDEX
    Explanations

    one of

    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
    users
    -0.58
    tors
    -0.58
     officers
    -0.54
     juges
    -0.52
    cshtml
    -0.52
     murderers
    -0.52
    romolecules
    -0.52
    enders
    -0.52
    onians
    -0.51
    ندگان
    -0.51
    POSITIVE LOGITS
     ModelExpression
    0.75
     Roskov
    0.65
    SequentialGroup
    0.65
    MessageOf
    0.63
     person
    0.63
     persoon
    0.60
     iprot
    0.60
     individuo
    0.58
    ]-->
    0.57
     člověk
    0.57
    Activations Density 0.004%

    No Known Activations