© 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. 2953
    Prev
    Next
    INDEX
    Explanations

    words and symbols in mathematical equations related to probability and distributions

    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
    ########.
    -1.32
    contentLoaded
    -1.16
     صوتيه
    -1.14
    
    -1.06
     الحره
    -1.04
    Personensuche
    -1.04
    awtextra
    -1.04
     تضيفلها
    -1.03
     BorderRadius
    -1.01
     Normdatei
    -0.99
    POSITIVE LOGITS
     pop
    0.57
    pop
    0.56
     O
    0.50
    (
    0.47
     N
    0.46
    Pop
    0.45
    ’
    0.45
     T
    0.44
    ínű
    0.44
    '
    0.44
    Activations Density 0.688%

    No Known Activations