© 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. 14030
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific scientific or statistical term related to model evaluation, such as a measure or coefficient

    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
    AndEndTag
    -0.81
     betweenstory
    -0.77
    expandindo
    -0.76
    ArrowToggle
    -0.73
    EndContext
    -0.69
    Билгалдахарш
    -0.68
    glLoadIdentity
    -0.68
     Principe
    -0.67
     useStyles
    -0.65
     utafitiHapana
    -0.64
    POSITIVE LOGITS
    soundcloud
    0.68
    agues
    0.66
     Torres
    0.65
    imgur
    0.61
    ildo
    0.61
    \}^{
    0.59
    getBytes
    0.59
    Torres
    0.58
     Capitol
    0.57
    DockStyle
    0.57
    Activations Density 0.081%

    No Known Activations