© 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. 600
    Prev
    Next
    INDEX
    Explanations

    the number 2 within mathematical formulas and equations

    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
    SourceChecksum
    -0.80
    CloseOperation
    -0.76
    forName
    -0.73
    StoryboardSegue
    -0.68
    initializeApp
    -0.67
     nakalista
    -0.67
    IndentedString
    -0.66
    tagHelperRunner
    -0.65
    XtraBars
    -0.64
    rrggbb
    -0.63
    POSITIVE LOGITS
     Hälfte
    0.69
     Half
    0.59
    一半
    0.59
    Half
    0.58
     half
    0.53
    half
    0.52
     Indies
    0.51
    SLASH
    0.51
     HALF
    0.50
     mitad
    0.50
    Activations Density 0.279%

    No Known Activations