© 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
    2. Gemma-2-2B
    3. 1-RES-MATRYOSHKA-DC
    4. 44
    Prev
    Next
    INDEX
    Explanations

    expressions involving inequalities, bounds, and mathematical relationships

    oai_token-act-pair · gpt-4.1-nano
    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
     escolar
    -0.43
    Reporter
    -0.42
     groot
    -0.40
     est
    -0.40
     orice
    -0.40
     preocupes
    -0.38
     films
    -0.38
    Films
    -0.38
    film
    -0.37
    ↵↵
    -0.36
    POSITIVE LOGITS
    }}_
    1.22
    _{
    1.16
    _\
    1.14
    }_
    1.14
     _{
    1.13
    )}_
    1.12
    }_\
    1.10
    $_
    1.09
    )$_
    1.08
    Datuak
    1.07
    Activations Density 7.018%

    No Known Activations