© 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. 1576
    Prev
    Next
    INDEX
    Explanations

    legal cases and their related details

    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
     in
    -0.66
     
    -0.60
     inter
    -0.55
     her
    -0.55
     a
    -0.54
     <
    -0.51
    iastes
    -0.51
     and
    -0.50
     of
    -0.50
     as
    -0.50
    POSITIVE LOGITS
     Theſe
    1.55
     Majefty
    1.43
     Anſ
    1.38
     Houſe
    1.35
     Efq
    1.34
     myſelf
    1.34
     Monfieur
    1.32
     ſeveral
    1.30
     Reſ
    1.29
     Jefus
    1.27
    Activations Density 3.368%

    No Known Activations