© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 1493
    Prev
    Next
    INDEX
    Explanations

    the word "and" preceded and followed by a number

    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
    χυ
    -0.51
    (
    -0.44
    R
    -0.42
    kozások
    -0.42
     Rússia
    -0.42
     russa
    -0.41
    owan
    -0.41
     belli
    -0.41
    Min
    -0.40
    \{
    -0.40
    POSITIVE LOGITS
    ंदीखरीदारी
    0.94
    GraphicsUnit
    0.87
    Abitanti
    0.84
    DockStyle
    0.83
     snippetHide
    0.83
     bezeichneter
    0.82
     Wicidata
    0.80
    RTLD
    0.80
    PerformLayout
    0.77
    UIControlState
    0.77
    Activations Density 0.739%

    No Known Activations