© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4038
    Prev
    Next
    INDEX
    Explanations

    characters

    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
     olvides
    -0.65
    клопе
    -0.59
    Remember
    -0.58
     culturelles
    -0.58
     przecież
    -0.55
     gyer
    -0.55
     scolaires
    -0.54
     <<<<<<<<<<<<<<
    -0.54
    Geplaatst
    -0.52
    nloa
    -0.51
    POSITIVE LOGITS
    UnusedPrivate
    0.59
     <>",
    0.57
    fhir
    0.56
    ühungen
    0.54
    ofire
    0.54
    AddTagHelper
    0.53
     fieldNum
    0.51
    LOO
    0.51
    osoba
    0.51
     prest
    0.51
    Activations Density 0.011%

    No Known Activations