© 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. 9614
    Prev
    Next
    INDEX
    Explanations

    phrases related to dependencies and variations in scientific contexts

    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
    MLLoader
    -0.71
    Rohy
    -0.57
    AndEndTag
    -0.56
    #+#
    -0.55
     насељу
    -0.55
    ModelAdmin
    -0.55
    EndProject
    -0.55
     виправивши
    -0.53
    EnableWeb
    -0.51
    脚注の使い方
    -0.51
    POSITIVE LOGITS
    ViewFeatures
    0.69
     defStyleAttr
    0.61
    enumi
    0.60
    smiley
    0.52
     jegy
    0.51
     observables
    0.48
     fascia
    0.48
    Sidenav
    0.48
     dimensionless
    0.48
    bibfield
    0.47
    Activations Density 0.089%

    No Known Activations