© 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. 92334
    Prev
    Next
    INDEX
    Explanations

    Data

    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
     appunto
    -0.47
     demek
    -0.41
     spirito
    -0.36
     j
    -0.35
     baju
    -0.33
     Eventually
    -0.32
     i
    -0.32
     r
    -0.32
    a
    -0.31
     hende
    -0.31
    POSITIVE LOGITS
    IntoConstraints
    1.44
     الرياضيه
    1.31
     propOrder
    1.22
    featureID
    1.18
    GEBURTSDATUM
    1.14
    ConstraintMaker
    1.13
     disambiguazione
    1.11
    elemField
    1.11
    EndGlobalSection
    1.10
    UnusedPrivate
    1.09
    Activations Density 0.078%

    No Known Activations