© 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. 90808
    Prev
    Next
    INDEX
    Explanations

    water and oceans

    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
     waters
    -1.34
    MigrationBuilder
    -1.21
     myſelf
    -1.13
    webElementXpaths
    -1.11
     itſelf
    -1.07
    waters
    -1.02
    UnusedPrivate
    -1.02
     Majefty
    -1.02
     seas
    -1.01
     ſche
    -1.00
    POSITIVE LOGITS
    .
    0.83
    ,
    0.82
     and
    0.82
     of
    0.74
     in
    0.66
     are
    0.60
     (
    0.60
    ;
    0.58
    cape
    0.55
     to
    0.54
    Activations Density 0.098%

    No Known Activations