© 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. 20-CLT-HP
    7. 75057
    Prev
    Next
    INDEX
    Explanations

    business and industry

    np_max-act-logits · 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
    IntoConstraints
    -0.74
     autorytatywna
    -0.70
    hões
    -0.60
    Referencie
    -0.58
     FishBase
    -0.56
    ագրություններ
    -0.56
    GOTREF
    -0.54
    MLLoader
    -0.52
    Sklici
    -0.52
    @[+][
    -0.51
    POSITIVE LOGITS
     means
    0.72
     Means
    0.60
     विश्वसनीयता
    0.59
    Means
    0.56
     things
    0.56
     trif
    0.55
    means
    0.54
    fony
    0.54
     protoimpl
    0.52
    ieR
    0.51
    Activations Density 0.000%

    No Known Activations