© 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. 2724
    Prev
    Next
    INDEX
    Explanations

    numerical digits starting with zero

    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
     AudioClip
    -0.51
    AndEndTag
    -0.50
    rhosis
    -0.47
     desc
    -0.47
     spontan
    -0.47
    deprecation
    -0.45
     der
    -0.45
    endregion
    -0.44
    éda
    -0.43
     Scalars
    -0.43
    POSITIVE LOGITS
    MigrationBuilder
    0.84
    styleType
    0.69
    AccessorTable
    0.68
     вікі
    0.63
    ügel
    0.63
    ValueStyle
    0.63
    IGraphics
    0.63
    mær
    0.62
    ništ
    0.60
    akaian
    0.60
    Activations Density 0.179%

    No Known Activations