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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 38750
    Prev
    Next
    INDEX
    Explanations

    T

    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
    T
    -1.55
     T
    -0.91
     purpoſe
    -0.74
    calipsis
    -0.72
    Ts
    -0.70
    PhysRevD
    -0.66
    windowFixed
    -0.65
    eet
    -0.65
     doInBackground
    -0.65
    t
    -0.65
    POSITIVE LOGITS
    ]-->
    0.44
    [](
    0.43
    mtd
    0.42
     ""],
    0.42
     متعلقه
    0.41
    即
    0.38
    ...@
    0.38
     tan
    0.36
    [{
    0.36
    ciech
    0.36
    Activations Density 2.104%

    No Known Activations