© 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. 30997
    Prev
    Next
    INDEX
    Explanations

    terms related to the visibility and management of features or names in a system

    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
     CreateTagHelper
    -1.09
     myſelf
    -0.93
     poffible
    -0.89
    脚注の使い方
    -0.88
    AndEndTag
    -0.83
    ſelf
    -0.82
     Eſ
    -0.82
     дописавши
    -0.82
    EndInit
    -0.81
     raiſ
    -0.81
    POSITIVE LOGITS
     addition
    0.46
     and
    0.45
     really
    0.45
    ->
    0.43
     mest
    0.42
     процентов
    0.40
     no
    0.40
    pruch
    0.40
     dragen
    0.40
     even
    0.40
    Activations Density 0.158%

    No Known Activations