© 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. 4289
    Prev
    Next
    INDEX
    Explanations

    development

    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
    WithIdentifier
    -0.54
     createState
    -0.52
    withIdentifier
    -0.50
    ftant
    -0.49
     pinulongan
    -0.47
    tabler
    -0.46
    maker
    -0.46
    thar
    -0.45
    BEAM
    -0.45
    belt
    -0.45
    POSITIVE LOGITS
     of
    0.74
     Roskov
    0.74
    Personensuche
    0.63
     católica
    0.62
    providedIn
    0.59
    NameInMap
    0.58
    OfWork
    0.55
    of
    0.55
    thâu
    0.54
     BoxFit
    0.54
    Activations Density 0.001%

    No Known Activations