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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3781
    Prev
    Next
    INDEX
    Explanations

    quantity

    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
     كومونز
    -0.53
     transférez
    -0.52
    ⓧ
    -0.47
    tahankan
    -0.47
    SuspendLayout
    -0.44
     bahwa
    -0.44
     Taktlose
    -0.44
    %)$
    -0.43
     genoux
    -0.43
     rằng
    -0.41
    POSITIVE LOGITS
     appearing
    0.71
     proofs
    0.68
     awaiting
    0.67
     theories
    0.65
     methods
    0.62
     waiting
    0.60
     occurring
    0.59
     opportunities
    0.58
     examples
    0.57
     arriving
    0.57
    Activations Density 0.002%

    No Known Activations