© 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. 1681
    Prev
    Next
    INDEX
    Explanations

    locations and names

    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
     Bur
    -1.14
    Bur
    -0.97
     bur
    -0.89
     BUR
    -0.81
     to
    -0.76
     Sp
    -0.74
     Bu
    -0.73
     Z
    -0.71
     Ber
    -0.71
     
    -0.67
    POSITIVE LOGITS
     myſelf
    1.30
     itſelf
    1.28
     Efq
    1.24
     raiſ
    1.16
     purpoſe
    1.12
     auffi
    1.11
     poffible
    1.10
     themſelves
    1.08
     uſ
    1.07
     reaſon
    1.07
    Activations Density 1.645%

    No Known Activations