© 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. 51
    Prev
    Next
    INDEX
    Explanations

    seemingly random, but mainly high values next to punctuation and single digits

    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
     ve
    -0.96
     m
    -0.94
     qu
    -0.92
     par
    -0.92
     f
    -0.91
     d
    -0.90
     v
    -0.90
     V
    -0.90
     et
    -0.89
     co
    -0.89
    POSITIVE LOGITS
     itſelf
    1.84
     Monfieur
    1.63
     myſelf
    1.61
     themſelves
    1.54
     Jefus
    1.53
     ſeveral
    1.52
     pleaſure
    1.50
     greateſt
    1.50
     himſelf
    1.48
     Theſe
    1.45
    Activations Density 4.012%

    No Known Activations