© 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. 29715
    Prev
    Next
    INDEX
    Explanations

    HTML list items and headings

    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
     myſelf
    -1.22
    CloseOperation
    -1.16
     itſelf
    -1.13
     Efq
    -1.09
    Geplaatst
    -1.06
     ſeveral
    -1.05
     Jefus
    -1.04
     purpoſe
    -1.04
     Monfieur
    -1.02
     pleaſure
    -1.00
    POSITIVE LOGITS
    u
    0.54
     et
    0.53
     B
    0.50
    <eos>
    0.49
     and
    0.46
     
    0.46
     =>
    0.46
     or
    0.45
    f
    0.45
    ,
    0.45
    Activations Density 0.046%

    No Known Activations