© 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. 3716
    Prev
    Next
    INDEX
    Explanations

    names or proper nouns, particularly those that start with 'L'

    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
    -0.59
     Johnnie
    -0.55
     Majefty
    -0.54
     tuc
    -0.53
     Monfieur
    -0.53
    accompagnement
    -0.53
    ableView
    -0.51
     stiefel
    -0.50
     pleaſure
    -0.50
     ¡¡
    -0.50
    POSITIVE LOGITS
    FormTagHelper
    0.75
    BeginContext
    0.75
    BeginInit
    0.74
    onghi
    0.70
    LookAnd
    0.68
    transQ
    0.68
    ValueStyle
    0.66
    principalTable
    0.65
     censo
    0.64
    userdetails
    0.62
    Activations Density 0.030%

    No Known Activations