© 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. 20-CLT-HP
    7. 71878
    Prev
    Next
    INDEX
    Explanations

    ending in 'old'/'est'/'esto'

    np_max-act-logits · 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
    LookAnd
    -0.77
     BoxFit
    -0.63
    invokeLater
    -0.62
    ArgsConstructor
    -0.61
     CommandType
    -0.60
    imize
    -0.59
    RTEE
    -0.58
     StatefulWidget
    -0.58
    DateTimeField
    -0.56
    ToAction
    -0.56
    POSITIVE LOGITS
    old
    0.62
    OLD
    0.52
    esting
    0.50
    olds
    0.50
    este
    0.49
     old
    0.49
    estos
    0.47
     coaster
    0.47
    olde
    0.46
    esto
    0.45
    Activations Density 0.010%

    No Known Activations