© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 97352
    Prev
    Next
    INDEX
    Explanations

    ilin

    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
    ilin
    -1.15
    ilina
    -0.43
    1
    -0.43
    otong
    -0.42
    entin
    -0.39
    ɦ
    -0.39
     particular
    -0.39
    just
    -0.38
     cư
    -0.38
    ecin
    -0.38
    POSITIVE LOGITS
     CreateTagHelper
    0.93
    ]--;
    0.81
     ModelExpression
    0.76
     Orrell
    0.73
    StoryboardSegue
    0.73
    Jeografia
    0.72
    DIPSETTING
    0.72
    Lähteet
    0.70
    GOTREF
    0.70
     kasarigan
    0.70
    Activations Density 1.636%

    No Known Activations