© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 95010
    Prev
    Next
    INDEX
    Explanations

    curly brackets

    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
    MigrationBuilder
    -0.82
     localObject
    -0.64
    sizeCache
    -0.62
    GEBURTSDATUM
    -0.62
    เฟ
    -0.59
    ange
    -0.58
    batore
    -0.56
    ագրություններ
    -0.53
     Administrativna
    -0.53
     विश्वसनीयता
    -0.52
    POSITIVE LOGITS
    AndEndTag
    0.60
    __':
    
    0.58
     favor
    0.56
    جوايز
    0.56
    BeginContext
    0.56
     favors
    0.52
     GenerationType
    0.50
    Grüsse
    0.50
    StoryboardSegue
    0.50
     favour
    0.49
    Activations Density 0.467%

    No Known Activations