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. 4-CLT-HP
    4. 3690
    Prev
    Next
    INDEX
    Explanations

    to

    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
     my
    -0.62
     the
    -0.57
     our
    -0.57
    BufferException
    -0.54
    enterOuterAlt
    -0.51
    GraphicsUnit
    -0.48
     хватает
    -0.47
     construction
    -0.46
     as
    -0.45
    zarchiwizowane
    -0.44
    POSITIVE LOGITS
    GEBURTSDATUM
    0.70
     uſe
    0.68
    =?";
    0.67
     ujednoznacz
    0.66
    KommentareTeilen
    0.65
     мәкал
    0.62
     دریافت‌شده
    0.61
    DispatchToProps
    0.60
     use
    0.60
    stdc
    0.59
    Activations Density 0.003%

    No Known Activations