© 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. 3-RES-MATRYOSHKA-DC
    7. 2271
    Prev
    Next
    INDEX
    Explanations

    the word "Bell"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     }}"></
    -0.69
    oult
    -0.68
    horabuena
    -0.62
    pozdrawiam
    -0.61
     Pool
    -0.60
    POOL
    -0.59
     Toibin
    -0.59
    mmate
    -0.59
     pooling
    -0.58
     }}$}
    -0.58
    POSITIVE LOGITS
     bell
    3.44
     Bell
    3.41
    Bell
    3.27
     BELL
    3.20
    bell
    2.97
     Bells
    2.72
    BELL
    2.66
     bells
    2.59
    bells
    2.30
     campana
    1.66
    Activations Density 0.037%

    No Known Activations