© 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. 3151
    Prev
    Next
    INDEX
    Explanations

    references to license or licensing information

    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
     ISNI
    -0.84
    TintMode
    -0.78
    TestingModule
    -0.77
    Rhestr
    -0.77
    Rüyada
    -0.76
    zeptember
    -0.73
    WaitGroup
    -0.73
    itinéraire
    -0.72
    IntoConstraints
    -0.72
     referenties
    -0.71
    POSITIVE LOGITS
    gen
    3.22
    Gen
    2.84
     gen
    2.83
     Gen
    2.73
    GEN
    2.42
     GEN
    2.08
    gens
    1.53
    ген
    1.51
     Generation
    1.27
     generation
    1.25
    Activations Density 0.071%

    No Known Activations