© 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. 30574
    Prev
    Next
    INDEX
    Explanations

    conditional phrases or hypothetical situations

    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
     play
    -0.70
    efined
    -0.68
    pea
    -0.66
    propertyName
    -0.65
     Hickman
    -0.65
     Burgess
    -0.65
    cch
    -0.65
    responseCode
    -0.65
    ResponseData
    -0.65
     Schaefer
    -0.64
    POSITIVE LOGITS
    AsUp
    0.90
    WebVitals
    0.89
    Personensuche
    0.87
    hadoop
    0.84
    ---*/
    0.81
    ंदीखरीदारी
    0.80
    Ifc
    0.77
     trypto
    0.77
    +:+
    0.75
     CreateTagHelper
    0.75
    Activations Density 0.272%

    No Known Activations