© 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. 5365
    Prev
    Next
    INDEX
    Explanations

    Holding/Physical Interaction

    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
    -0.46
     éti
    -0.43
    tag
    -0.40
    ouille
    -0.40
    المناصب
    -0.40
     ciel
    -0.39
    cat
    -0.38
     alza
    -0.38
     emel
    -0.38
     Attic
    -0.38
    POSITIVE LOGITS
    Parcelize
    0.73
    prepareStatement
    0.72
     onCreateView
    0.70
    rungsseite
    0.65
    copg
    0.64
    posedge
    0.63
     propOrder
    0.63
    MLLoader
    0.63
    GeneratedCode
    0.63
     AssemblyProduct
    0.61
    Activations Density 0.001%

    No Known Activations