© 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. 2-RES-MATRYOSHKA-DC
    7. 3053
    Prev
    Next
    INDEX
    Explanations

    references to uncertain or variable occurrences or frequency

    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
     likely
    -1.09
     Likely
    -1.06
    Likely
    -1.02
    Geplaatst
    -0.98
    likely
    -0.95
     Typically
    -0.81
    aktery
    -0.78
    Typically
    -0.78
     dürfte
    -0.74
    OGND
    -0.72
    POSITIVE LOGITS
     sometimes
    2.64
    sometimes
    2.45
     Sometimes
    2.31
    Sometimes
    2.25
     manchmal
    2.00
     ibland
    2.00
     parfois
    1.99
     occasionally
    1.78
     иногда
    1.75
     soms
    1.71
    Activations Density 0.011%

    No Known Activations