© 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. 3118
    Prev
    Next
    INDEX
    Explanations

    references to specific identifiable data entries, codes, or structured metadata such as IDs and timestamps

    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
     disambiguazione
    -0.63
    abstractmethod
    -0.57
     surla
    -0.52
     IMDG
    -0.51
    ภัณฑ์
    -0.51
    DotNetBar
    -0.50
    OSSARY
    -0.49
    __*/
    -0.48
    qiao
    -0.48
     незавершена
    -0.47
    POSITIVE LOGITS
    enumii
    0.71
    ReusableCell
    0.70
    WindowConstants
    0.69
    ArgsConstructor
    0.68
    aryen
    0.67
    bootstrapcdn
    0.66
    Laure
    0.65
     Gaulle
    0.64
     Pegasus
    0.64
     numberOfRows
    0.63
    Activations Density 0.341%

    No Known Activations