© 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. 26708
    Prev
    Next
    INDEX
    Explanations

    references to structured parts or sections of a document, such as panels or clauses

    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
    StoryboardSegue
    -0.68
     fotografico
    -0.53
     gravedad
    -0.52
     esempi
    -0.51
     nematode
    -0.50
     camada
    -0.49
     laikā
    -0.49
     mesmos
    -0.48
     mesmas
    -0.48
     avancée
    -0.48
    POSITIVE LOGITS
    (!__
    0.69
     виправивши
    0.67
     فريبيس
    0.66
    ⓧ
    0.65
     Ib
    0.63
    disposing
    0.61
    mandu
    0.61
     дописавши
    0.60
     nakalista
    0.60
    AutoresizingMask
    0.60
    Activations Density 0.016%

    No Known Activations