Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 39199
    Prev
    Next
    INDEX
    Explanations

    SP

    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
     SP
    -0.73
     
    -0.69
     the
    -0.59
     P
    -0.56
     V
    -0.54
     Sp
    -0.54
    SP
    -0.51
     S
    -0.51
     Mar
    -0.51
     N
    -0.50
    POSITIVE LOGITS
     itſelf
    1.05
     CreateTagHelper
    1.04
     виправивши
    1.02
    Diwedd
    0.93
     disambiguazione
    0.93
    ſelf
    0.92
     tfsi
    0.92
    kloped
    0.92
     myſelf
    0.92
     InputDecoration
    0.90
    Activations Density 0.255%

    No Known Activations