© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 95179
    Prev
    Next
    INDEX
    Explanations

    early

    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
     early
    -2.13
    early
    -1.85
    Early
    -1.79
     Early
    -1.67
     earliest
    -1.59
     EARLY
    -1.58
    EARLY
    -1.42
     frühen
    -1.30
    早期
    -1.17
     temprano
    -1.09
    POSITIVE LOGITS
    
    0.64
    TagMode
    0.62
     Chwiliwch
    0.62
    alline
    0.62
    esez
    0.60
     تضيفلها
    0.60
     autorytatywna
    0.60
    devamını
    0.59
     صوتيه
    0.59
    stridium
    0.59
    Activations Density 0.069%

    No Known Activations