© 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. 170
    Prev
    Next
    INDEX
    Explanations

    mathematical formula syntax

    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
    genheit
    -0.73
    [toxicity=0]
    -0.73
     Maru
    -0.71
     Menon
    -0.70
     Schroeder
    -0.69
    𝐮
    -0.69
    𝐳
    -0.68
     Anz
    -0.67
    brot
    -0.66
    ж
    -0.66
    POSITIVE LOGITS
     raiſ
    1.18
     iſt
    1.16
     uſed
    1.07
     Anſ
    1.05
     pleaſure
    1.04
     ſever
    1.03
     myſelf
    1.02
    expandindo
    1.00
     AssemblyVersion
    0.98
    ))).
    0.98
    Activations Density 5.116%

    No Known Activations