© 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
    2. Gemma-2-2B
    3. 3-RES-MATRYOSHKA-DC
    4. 1045
    Prev
    Next
    INDEX
    Explanations

    the term "mid" and related terms referring to a middle position, size, or state, often in combination with other adjectives like "low," "late," or "sized"

    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
    :✨
    -0.87
     opérateur
    -0.67
    requireNonNull
    -0.65
    enoord
    -0.63
     officio
    -0.63
     AssemblyProduct
    -0.63
    المكان
    -0.62
    CloseOperation
    -0.62
     nawr
    -0.61
     كومونز
    -0.61
    POSITIVE LOGITS
     mid
    2.59
     middle
    2.48
     Mid
    2.33
    middle
    2.28
    Mid
    2.27
    Middle
    2.19
    mid
    2.16
     Middle
    2.16
     MIDDLE
    2.14
     MID
    2.02
    Activations Density 0.459%

    No Known Activations