© 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. 3-RES-MATRYOSHKA-DC
    7. 3033
    Prev
    Next
    INDEX
    Explanations

    mathematical and scientific texts stating equations or giving definitions

    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
    ^(@)
    -0.93
    ſelves
    -0.84
    neſs
    -0.81
     tartalomajánló
    -0.79
    ſelf
    -0.77
    ftance
    -0.77
     Efq
    -0.75
     Anſ
    -0.75
     تضيفلها
    -0.74
    utilisons
    -0.74
    POSITIVE LOGITS
    n
    0.49
     n
    0.47
    :
    0.46
    ↵↵
    0.45
    Read
    0.45
    得
    0.45
     read
    0.44
    ${\
    0.42
    派
    0.42
    म्
    0.41
    Activations Density 0.631%

    No Known Activations