© 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. 12-RES-MATRYOSHKA-DC
    7. 22950
    Prev
    Next
    INDEX
    Explanations

    the frequency of the word "Johnson" in the text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    es
    -0.73
     Sche
    -0.69
     Cale
    -0.68
    times
    -0.66
    ü
    -0.66
     scenes
    -0.65
    клопе
    -0.65
     lou
    -0.64
     Vla
    -0.64
     Beres
    -0.64
    POSITIVE LOGITS
     Johnson
    1.92
     johnson
    1.78
     JOHNSON
    1.77
    Johnson
    1.77
    NSON
    1.70
    johnson
    1.55
    JOH
    1.21
     Jonson
    1.06
    ValueStyle
    1.04
    nson
    1.02
    Activations Density 0.004%

    No Known Activations