© 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. 1-CLT-HP
    4. 46246
    Prev
    Next
    INDEX
    Explanations

    Named entities

    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
    SequentialGroup
    -0.67
    WriteTagHelper
    -0.60
    addPreferredGap
    -0.59
    BufferException
    -0.57
    OrNil
    -0.53
     puestos
    -0.52
     onCancelled
    -0.52
     GenerationType
    -0.51
     typelib
    -0.51
    Hauptartikel
    -0.51
    POSITIVE LOGITS
     Efq
    0.70
    zelfde
    0.61
     myſelf
    0.56
     itſelf
    0.55
     Pyrenees
    0.54
     Chriſt
    0.53
     VizieR
    0.53
    abbr
    0.53
     Anſ
    0.52
     Eſ
    0.51
    Activations Density 0.106%

    No Known Activations