© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2603
    Prev
    Next
    INDEX
    Explanations

    fold

    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
     مرئيه
    -0.54
    참고
    -0.54
    })->
    -0.52
    исленность
    -0.51
     Lokales
    -0.51
    abestanden
    -0.51
    getRuntime
    -0.48
    )$/,
    -0.47
     Abp
    -0.46
     TAMBÉM
    -0.45
    POSITIVE LOGITS
     préparé
    0.56
    notated
    0.56
     prepared
    0.55
    OutputType
    0.51
    блон
    0.50
     adapted
    0.50
     متعلقه
    0.49
    bited
    0.49
    睹
    0.49
    onsor
    0.48
    Activations Density 0.000%

    No Known Activations