© 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. 6864
    Prev
    Next
    INDEX
    Explanations

    patterns related to string data or code snippets

    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
     String
    -0.97
     toString
    -0.69
    EndGlobalSection
    -0.63
     JComboBox
    -0.63
    LEncoder
    -0.62
     Numerade
    -0.60
    EqualsAnd
    -0.57
    String
    -0.57
    oporosis
    -0.57
     StringTokenizer
    -0.56
    POSITIVE LOGITS
    string
    1.31
     Efq
    0.72
     ainfi
    0.68
     fevere
    0.66
     faſt
    0.66
     poffible
    0.65
     diſt
    0.65
     crdi
    0.64
     laſt
    0.64
     iſt
    0.63
    Activations Density 0.022%

    No Known Activations