© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 10126
    Prev
    Next
    INDEX
    Explanations

    segment identifiers or roles in a musical or performance context

    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
    HomeAsUpEnabled
    -0.58
     بيها
    -0.57
    verwijspagina
    -0.53
    onema
    -0.53
    Personendaten
    -0.53
    ablon
    -0.52
    <caption>
    -0.52
     $__
    -0.49
    #+#
    -0.47
    anxi
    -0.46
    POSITIVE LOGITS
    windowFixed
    0.81
    PreferredItem
    0.71
     ExecuteAsync
    0.71
    AutoField
    0.70
    InjectAttribute
    0.69
     informée
    0.65
    astify
    0.61
    ValueStyle
    0.61
    UnusedPrivate
    0.60
    />,
    0.60
    Activations Density 0.002%

    No Known Activations