© 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. 14679
    Prev
    Next
    INDEX
    Explanations

    elements related to weekly book discussion prompts

    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
    +#+#
    -0.55
    hile
    -0.45
    Concentr
    -0.45
    ★★★★☆
    -0.44
     collection
    -0.43
     roba
    -0.43
     Collection
    -0.42
     />);
    -0.41
     gesch
    -0.41
    lée
    -0.41
    POSITIVE LOGITS
    клопе
    0.88
    httphttps
    0.88
    gameserver
    0.79
    UnusedPrivate
    0.79
    MigrationBuilder
    0.78
     OFDb
    0.76
    WebControls
    0.76
     Majefty
    0.75
    ftagPool
    0.75
     pleaſure
    0.74
    Activations Density 0.053%

    No Known Activations