© 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. 4-CLT-HP
    7. 4742
    Prev
    Next
    INDEX
    Explanations

    my

    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
    ImageContext
    -0.99
     propOrder
    -0.83
     CURIAM
    -0.77
     ModelExpression
    -0.77
    oredCriteria
    -0.76
    StoryboardSegue
    -0.75
    principalColumn
    -0.74
    webElementXpaths
    -0.74
    SerializedSize
    -0.74
     chi̍t
    -0.74
    POSITIVE LOGITS
    ,‎
    0.44
     lives
    0.41
     cheek
    0.35
     mouth
    0.35
     cars
    0.34
    قایناق‌لار
    0.33
    copg
    0.33
     life
    0.33
     faces
    0.33
    ścią
    0.32
    Activations Density 0.010%

    No Known Activations