© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 14097
    Prev
    Next
    INDEX
    Explanations

    references to tools, site maps, or processes related to website and server management

    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
    __*/
    -0.66
    Personensuche
    -0.64
    ViewImports
    -0.62
    execSQL
    -0.60
    mtg
    -0.60
    Composable
    -0.58
     الحره
    -0.57
    mobileqq
    -0.57
     ostavi
    -0.56
     CreateTagHelper
    -0.56
    POSITIVE LOGITS
     uniquely
    2.58
     distinctly
    1.20
     peculiarly
    1.13
    quely
    0.98
     distin
    0.94
     singularly
    0.80
    ellow
    0.59
    恰
    0.58
    baix
    0.57
     BrowserModule
    0.54
    Activations Density 0.001%

    No Known Activations