© 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. 3-RES-MATRYOSHKA-DC
    7. 2220
    Prev
    Next
    INDEX
    Explanations

    code snippets including hyphenated words, sizing and maximum values

    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
     للاسماء
    -0.56
     Combien
    -0.51
     générale
    -0.48
    persist
    -0.46
     quelconque
    -0.45
    enza
    -0.43
    ө
    -0.43
    nitus
    -0.42
     mio
    -0.42
     pén
    -0.41
    POSITIVE LOGITS
    IntoConstraints
    0.84
    UserScript
    0.74
    MigrationBuilder
    0.72
    FormTagHelper
    0.69
    RenderAtEndOf
    0.69
     dore
    0.65
    ronpa
    0.65
     metav
    0.64
    tagHelperRunner
    0.63
     handleMessage
    0.63
    Activations Density 0.891%

    No Known Activations