© 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. 12-RES-MATRYOSHKA-DC
    7. 15184
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives describing size and complexity

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
     p
    -0.81
     x
    -0.80
     more
    -0.79
     Z
    -0.79
     to
    -0.78
     X
    -0.77
     D
    -0.75
     j
    -0.75
     T
    -0.74
     let
    -0.74
    POSITIVE LOGITS
     myſelf
    1.80
     itſelf
    1.74
    ſelf
    1.70
     himſelf
    1.68
     pleaſure
    1.63
     Anſ
    1.56
     Jefus
    1.54
     Majefty
    1.54
     themſelves
    1.52
     Theſe
    1.52
    Activations Density 0.088%

    No Known Activations