© 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. 0-CLT-HP
    7. 1299
    Prev
    Next
    INDEX
    Explanations

    Sbury

    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
     itſelf
    -1.32
     myſelf
    -1.22
    ſelf
    -1.07
     Efq
    -1.07
     doubtnut
    -1.05
    ſelves
    -1.02
     purpoſe
    -1.02
     pleaſure
    -1.02
     ſche
    -1.01
     Majefty
    -1.01
    POSITIVE LOGITS
    ,
    0.73
     in
    0.62
     much
    0.60
     to
    0.58
     for
    0.58
     K
    0.58
    .
    0.58
     and
    0.56
     T
    0.56
     
    0.56
    Activations Density 1.817%

    No Known Activations