© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96313
    Prev
    Next
    INDEX
    Explanations

    technical/research

    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
    annica
    -0.59
     quinta
    -0.57
     Vey
    -0.55
    Obrázky
    -0.54
     fifth
    -0.54
     Permanente
    -0.54
     Kitchener
    -0.53
     Conqueror
    -0.52
    dBm
    -0.52
     modelling
    -0.51
    POSITIVE LOGITS
    CloseOperation
    0.59
     FetchType
    0.57
     orar
    0.51
     חיצוניים
    0.51
    DebuggerStep
    0.44
    WriteLiteral
    0.42
    FormTagHelper
    0.41
    zlich
    0.41
    GOTREF
    0.41
    getMenuInflater
    0.41
    Activations Density 0.001%

    No Known Activations