© 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. 22-RES-MATRYOSHKA-DC
    7. 41
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    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.22.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.22.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
     Shakspeare
    -0.80
     Houſe
    -0.73
     Reſ
    -0.73
     Ichigo
    -0.69
     ragaz
    -0.68
     sasuke
    -0.68
     Athene
    -0.68
     Cæsar
    -0.68
     ALR
    -0.68
     jupiter
    -0.68
    POSITIVE LOGITS
     his
    1.16
     him
    1.15
     he
    1.02
     Mr
    1.02
     John
    0.99
     David
    0.97
     James
    0.91
     Richard
    0.91
     He
    0.91
     Dr
    0.90
    Activations Density 9.581%

    No Known Activations