© 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. 45642
    Prev
    Next
    INDEX
    Explanations

    shells, tails

    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
    -1.41
     myſelf
    -1.32
     Efq
    -1.27
     pleaſure
    -1.23
     Jefus
    -1.21
     purpoſe
    -1.21
     Majefty
    -1.19
     ſche
    -1.16
    ſelf
    -1.15
     ་་
    -1.14
    POSITIVE LOGITS
     of
    0.69
    ,
    0.69
    .
    0.68
     in
    0.63
     on
    0.60
     to
    0.60
     (
    0.59
     for
    0.57
     that
    0.57
     at
    0.52
    Activations Density 1.643%

    No Known Activations