© 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. 5935
    Prev
    Next
    INDEX
    Explanations

    advertising

    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
    Geplaatst
    -0.73
     mergeFrom
    -0.70
    Diweddarwch
    -0.66
    ParallelGroup
    -0.62
    expandindo
    -0.60
    rungsseite
    -0.59
    SharedCtor
    -0.58
    parsedMessage
    -0.58
     ProtoMessage
    -0.58
    setof
    -0.58
    POSITIVE LOGITS
     science
    0.68
     Science
    0.61
     technology
    0.60
     business
    0.53
     law
    0.53
     management
    0.52
     control
    0.51
     resource
    0.51
     sciences
    0.50
     kasarigan
    0.50
    Activations Density 0.001%

    No Known Activations