© 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. 92234
    Prev
    Next
    INDEX
    Explanations

    able/ible

    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
    able
    -1.64
    ABLE
    -1.28
    ise
    -1.02
    ables
    -0.82
    ABLES
    -0.77
    ISE
    -0.75
    ably
    -0.69
    abled
    -0.62
    ,
    -0.62
    ises
    -0.62
    POSITIVE LOGITS
    MigrationBuilder
    1.34
     myſelf
    1.34
     snippetHide
    1.30
    RectangleBorder
    1.30
    rungsseite
    1.29
     Efq
    1.29
    endphp
    1.28
    IsContent
    1.27
     defaultstate
    1.26
    principalColumn
    1.23
    Activations Density 1.920%

    No Known Activations