© 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. 23413
    Prev
    Next
    INDEX
    Explanations

    words associated with disorder and confusion

    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
    Negative Logits
    ApiModelProperty
    -0.78
    ecore
    -0.76
    JsonPropertyName
    -0.70
    IBarButtonItem
    -0.70
     CanadaChoose
    -0.69
    Tikang
    -0.68
    LookAnd
    -0.67
     Alde
    -0.66
    Халык
    -0.64
    AutoresizingMask
    -0.64
    POSITIVE LOGITS
     mess
    1.27
     messy
    1.25
     chaos
    1.23
     Mess
    1.20
     messes
    1.13
    Mess
    1.12
    Chaos
    1.10
     caos
    1.07
    chaos
    1.05
     Chaos
    1.05
    Activations Density 0.035%

    No Known Activations