© 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. 10383
    Prev
    Next
    INDEX
    Explanations

    instances of the word "shown," indicating reported evidence or findings in a study

    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
    Datuak
    -0.98
     ftate
    -0.88
     Jefus
    -0.86
     ſtate
    -0.85
     Monfieur
    -0.84
    webElementXpaths
    -0.83
     "..\..\..\
    -0.82
    addCriterion
    -0.81
     houſe
    -0.81
     poffible
    -0.81
    POSITIVE LOGITS
     AssemblyCulture
    0.65
     capa
    0.56
    GOTREF
    0.56
    falcon
    0.53
     distancia
    0.52
    dfunding
    0.52
    figcaption
    0.52
    ManyToMany
    0.51
     in
    0.50
    bibliothek
    0.50
    Activations Density 0.022%

    No Known Activations