© 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. 0-CLT-HP
    7. 92800
    Prev
    Next
    INDEX
    Explanations

    technical/academic writing

    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
     enter
    -1.30
    enter
    -1.08
     Enter
    -1.03
    Enter
    -1.02
    ENTER
    -0.84
     entering
    -0.75
     ENTER
    -0.60
     Entering
    -0.59
    entered
    -0.57
    diger
    -0.56
    POSITIVE LOGITS
     utafitiHapana
    0.75
    i
    0.71
    o
    0.70
     مشين
    0.69
     pulumi
    0.66
     OkHttpClient
    0.65
    OGND
    0.64
    oneph
    0.63
     Urqu
    0.61
    AsUp
    0.60
    Activations Density 1.428%

    No Known Activations