© 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. 4-CLT-HP
    7. 4595
    Prev
    Next
    INDEX
    Explanations

    actually

    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
     Chwiliwch
    -0.79
    ⓧ
    -0.64
    contentLoaded
    -0.64
     démocr
    -0.62
     étoient
    -0.60
    ]")]
    -0.59
     réfrig
    -0.59
     avoient
    -0.58
    تقاوى
    -0.56
    localctx
    -0.56
    POSITIVE LOGITS
     INTERESAR
    0.64
    chapper
    0.56
     الحره
    0.56
     blockade
    0.56
    URIComponent
    0.53
     tailor
    0.50
     monitor
    0.49
    apha
    0.49
    æk
    0.49
    rophes
    0.48
    Activations Density 0.003%

    No Known Activations