© 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. 2-RES-MATRYOSHKA-DC
    7. 3577
    Prev
    Next
    INDEX
    Explanations

    the presence of specific words or phrases in a document, particularly names and terms related to organizations, locations, or individuals

    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
     snippetHide
    -0.91
    帖最后由
    -0.89
    ConstraintMaker
    -0.88
    InjectAttribute
    -0.86
     disambiguazione
    -0.78
    ContentAsync
    -0.77
    OGND
    -0.77
    MemoryWarning
    -0.75
     nahilalakip
    -0.75
    tagHelperRunner
    -0.71
    POSITIVE LOGITS
    rån
    0.55
    ExecuteReader
    0.53
    DotNetBar
    0.47
     berlaku
    0.47
     sierpnia
    0.46
    Beskrivning
    0.46
     finns
    0.46
     TextAppearance
    0.46
     tertentu
    0.45
     måste
    0.45
    Activations Density 0.154%

    No Known Activations