© 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. 1121
    Prev
    Next
    INDEX
    Explanations

    capitalized proper names often beginning with the letter "L" or "S"

    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
     Anſ
    -1.08
     Theſe
    -1.07
     Houſe
    -1.02
     ་་
    -1.01
     houſe
    -1.00
     faſt
    -0.99
     ſind
    -0.94
     Beſ
    -0.93
     verſ
    -0.93
     Diſ
    -0.93
    POSITIVE LOGITS
    Ra
    0.77
     Se
    0.74
     Ra
    0.73
     Ge
    0.72
    Ma
    0.72
     Sa
    0.71
    Sa
    0.70
    Ge
    0.70
    Di
    0.69
    Se
    0.69
    Activations Density 1.004%

    No Known Activations