© 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. 31080
    Prev
    Next
    INDEX
    Explanations

    objects represented by empty objects or dictionaries in data structures

    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
    <i>
    -0.66
    <blockquote>
    -0.65
    <b>
    -0.62
    end
    -0.59
    ina
    -0.59
    we
    -0.59
    </td>
    -0.58
    ere
    -0.57
    </i>
    -0.56
    in
    -0.56
    POSITIVE LOGITS
    FormTagHelper
    0.93
     Holman
    0.88
    ProcessEvent
    0.82
     AppCompat
    0.82
    olesale
    0.81
    endroit
    0.81
    idać
    0.81
     pinulongan
    0.81
    arranty
    0.81
     himſelf
    0.81
    Activations Density 0.015%

    No Known Activations