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. 5-CLT-HP
    4. 1801
    Prev
    Next
    INDEX
    Explanations

    Code/License agreements

    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
     of
    -0.56
     ben
    -0.45
    toolkit
    -0.45
     acte
    -0.41
    OLOGIA
    -0.40
    SortOrder
    -0.40
     względu
    -0.39
    hoeddwyd
    -0.39
     Of
    -0.39
     
    -0.38
    POSITIVE LOGITS
     autorytatywna
    0.70
     resourceCulture
    0.69
    forChild
    0.69
    issipp
    0.65
    multer
    0.65
    IntoConstraints
    0.64
    StoryboardSegue
    0.63
    Datuak
    0.61
    ValueGeneration
    0.61
    addCriterion
    0.60
    Activations Density 0.002%

    No Known Activations