© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 1585
    Prev
    Next
    INDEX
    Explanations

    instances of the word "focus" or its derivatives, often followed by "on"

    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
    lblNewLabel
    -0.68
    brtc
    -0.67
    databind
    -0.63
    umab
    -0.60
    CodeDom
    -0.60
     PLAT
    -0.59
     plat
    -0.59
    ActionButton
    -0.59
    printLine
    -0.58
     Schalke
    -0.58
    POSITIVE LOGITS
     focus
    3.02
     concentrate
    2.73
     Focus
    2.70
    Focus
    2.66
    focus
    2.66
     concentrating
    2.58
     concentrates
    2.53
     focuses
    2.52
     focused
    2.48
     focusing
    2.48
    Activations Density 0.515%

    No Known Activations