© 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. 18-RES-MATRYOSHKA-DC
    7. 210
    Prev
    Next
    INDEX
    Explanations

    numerical digits and periods within question prompts

    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/blocks.18.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.50
    Politik
    -0.47
    lık
    -0.46
    談社
    -0.44
     الحره
    -0.43
    itol
    -0.40
    complexContent
    -0.40
    σμα
    -0.39
    MockMvc
    -0.39
    itel
    -0.39
    POSITIVE LOGITS
    8
    1.12
     Eighth
    1.02
     eighth
    1.02
     eight
    0.99
     Eight
    0.98
     EIGHT
    0.94
     VIII
    0.93
    Eight
    0.91
     eighty
    0.85
     Eighty
    0.84
    Activations Density 2.109%

    No Known Activations