© 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. 1-RES-MATRYOSHKA-DC
    7. 459
    Prev
    Next
    INDEX
    Explanations

    references to the word "out" used as an adjective or noun indicating a state or classification

    oai_token-act-pair · gpt-4.1-nano
    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
     للمعارف
    -0.87
     صوتيه
    -0.75
     protoimpl
    -0.73
    expandindo
    -0.63
    cosity
    -0.61
    rungsseite
    -0.60
    iyle
    -0.60
    eradish
    -0.57
    etheless
    -0.56
     Bioaccumulative
    -0.56
    POSITIVE LOGITS
     out
    4.19
     Out
    3.56
    out
    3.52
    Out
    3.45
     OUT
    3.36
    OUT
    2.88
     outs
    2.52
    outs
    2.41
    アウト
    2.20
    getOut
    2.11
    Activations Density 0.547%

    No Known Activations