© 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. 3805
    Prev
    Next
    INDEX
    Explanations

    this

    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
    Autoritní
    -0.64
     extré
    -0.64
     HasFactory
    -0.64
     optique
    -0.61
     électron
    -0.59
     ménages
    -0.57
     digitais
    -0.56
     constitué
    -0.56
    yntaxException
    -0.56
     duquel
    -0.56
    POSITIVE LOGITS
     past
    0.59
    økt
    0.57
    DataAnnotations
    0.48
     month
    0.48
     balik
    0.45
     FishBase
    0.44
     mese
    0.44
     recently
    0.42
    AutoField
    0.42
     ivi
    0.42
    Activations Density 0.009%

    No Known Activations