© 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. 0-RES-MATRYOSHKA-DC
    7. 13087
    Prev
    Next
    INDEX
    Explanations

    measurements related to mechanical stress and pressure in the material

    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
    emas
    -0.47
    ModelSerializer
    -0.46
     Futter
    -0.46
     TestBed
    -0.44
     XNUMX
    -0.43
    abetes
    -0.42
    Personensuche
    -0.42
     AVC
    -0.42
    icose
    -0.41
    artney
    -0.41
    POSITIVE LOGITS
     समीक्षक
    0.82
    OGND
    0.78
    UnsafeEnabled
    0.73
    تقاوى
    0.70
    __))
    0.69
    setVerticalGroup
    0.68
    ++]
    0.66
    MergeFrom
    0.65
    }{*}{}
    0.62
    BufferException
    0.61
    Activations Density 0.585%

    No Known Activations