© 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. 6-RES-MATRYOSHKA-DC
    7. 898
    Prev
    Next
    INDEX
    Explanations

    the word "String" or "string" in different capitalizations along with associated punctuation and numbers

    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
    ChildScrollView
    -0.69
    jeb
    -0.64
    Reducers
    -0.63
     Toe
    -0.63
     Leve
    -0.62
     leek
    -0.62
    iestety
    -0.62
     Partagez
    -0.60
     nắm
    -0.60
     Siete
    -0.60
    POSITIVE LOGITS
     strings
    1.66
     Stringer
    1.55
     string
    1.51
    strings
    1.51
     Strings
    1.46
    string
    1.41
     STRING
    1.36
     String
    1.35
    STRING
    1.35
    Strings
    1.31
    Activations Density 0.152%

    No Known Activations