© 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. 2-RES-MATRYOSHKA-DC
    7. 4582
    Prev
    Next
    INDEX
    Explanations

    references to the method of measurement or calculation used in scientific analyses

    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
    GridColumn
    -0.72
    anggil
    -0.70
    zulka
    -0.66
     Callahan
    -0.65
    Xna
    -0.62
    BeforeEach
    -0.60
    ądź
    -0.60
     conversely
    -0.59
    Parcelize
    -0.59
    byen
    -0.59
    POSITIVE LOGITS
     means
    0.90
    means
    0.81
    Means
    0.64
    Према
    0.63
     Means
    0.62
     MEANS
    0.55
    fml
    0.50
    MigrationBuilder
    0.50
    ═
    0.47
     biais
    0.46
    Activations Density 0.091%

    No Known Activations