© 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. 2-RES-MATRYOSHKA-DC
    7. 5221
    Prev
    Next
    INDEX
    Explanations

    sequences associated with specific codes or identifiers, particularly those involving standard formatting or structured codes

    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
    存于互联网档案馆
    -0.89
    mybatisplus
    -0.79
     resourceCulture
    -0.74
    ChildScrollView
    -0.73
     nakalista
    -0.70
     Италијани
    -0.67
    UserScript
    -0.65
    ActionCreators
    -0.64
     StatelessWidget
    -0.63
    SerializedSize
    -0.63
    POSITIVE LOGITS
     getIs
    0.54
    gant
    0.52
     tartalomajánló
    0.51
     Bio
    0.49
    gaven
    0.47
    WindowConstants
    0.47
     pory
    0.46
    POSIT
    0.45
     ней
    0.45
    ']):
    0.45
    Activations Density 0.058%

    No Known Activations