© 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. 6288
    Prev
    Next
    INDEX
    Explanations

    references to meta-analyses and systematic reviews

    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
    mergeFrom
    -0.63
    RegistryLite
    -0.62
    :✨
    -0.61
    CloseOperation
    -0.61
     ErrIntOverflow
    -0.61
     HasFactory
    -0.60
    FieldBuilder
    -0.59
    <[
    -0.59
    FunctionFlags
    -0.59
     MessageBoxIcon
    -0.59
    POSITIVE LOGITS
    SequentialGroup
    0.53
    crites
    0.49
    costal
    0.48
    Pulling
    0.47
     daz
    0.46
     numerator
    0.46
    eseorang
    0.46
    RCT
    0.46
     RTS
    0.45
    accumulator
    0.44
    Activations Density 0.720%

    No Known Activations