© 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. 4-CLT-HP
    7. 648
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    …
    -0.50
    ↵↵
    -0.47
    <bos>
    -0.46
    -
    -0.45
     "..\..\..\
    -0.44
    !
    -0.42
    ↵
    -0.42
     Hoffman
    -0.42
     …
    -0.41
    '
    -0.41
    POSITIVE LOGITS
    ]")]
    0.82
    Portály
    0.77
     bağlantılar
    0.69
    RTDA
    0.67
     تضيفلها
    0.66
     réessayer
    0.65
     estimés
    0.65
     étoit
    0.63
     Efq
    0.63
     ujednoznacz
    0.62
    Activations Density 0.031%

    No Known Activations