© 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. 98168
    Prev
    Next
    INDEX
    Explanations

    code or programming

    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
     kasarigan
    -0.77
    Datuak
    -0.67
    addCriterion
    -0.63
    uxxxx
    -0.62
     فريبيس
    -0.60
     pinulongan
    -0.56
    SourceChecksum
    -0.55
     OFDb
    -0.52
    jenost
    -0.52
    titleMargin
    -0.50
    POSITIVE LOGITS
     harp
    0.53
     dials
    0.51
    isms
    0.49
     hatch
    0.48
     Thebes
    0.48
     bellows
    0.48
     shipwreck
    0.47
    ństw
    0.47
     shafts
    0.47
     Efq
    0.47
    Activations Density 0.003%

    No Known Activations