© 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. 1202
    Prev
    Next
    INDEX
    Explanations

    the number zero and the percentage symbol

    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
     MotionEvent
    -0.92
     @"/
    -0.81
     ddelweddau
    -0.75
    knapp
    -0.75
    PyTuple
    -0.72
     getopt
    -0.71
    databind
    -0.69
     propOrder
    -0.67
    lapsingToolbar
    -0.67
    jsdelivr
    -0.67
    POSITIVE LOGITS
    KommentareTeilen
    0.62
     Idea
    0.50
    laient
    0.49
     MaterialApp
    0.47
     NEV
    0.47
    adaran
    0.46
    ion
    0.46
    bez
    0.46
     teg
    0.45
     Gies
    0.45
    Activations Density 0.295%

    No Known Activations