© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 14726
    Prev
    Next
    INDEX
    Explanations

    phrases related to statistical analysis and significant findings in data

    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
    nonatomic
    -0.45
     nonatomic
    -0.44
     calorie
    -0.43
     initComponents
    -0.41
     Richter
    -0.40
    crat
    -0.40
    cault
    -0.39
    bustible
    -0.39
     Ang
    -0.38
     Cal
    -0.38
    POSITIVE LOGITS
    AndroidJUnit
    0.74
     وتسجيلات
    0.68
    setVerticalGroup
    0.66
     purpoſe
    0.64
    UnknownFieldSet
    0.64
     ainfi
    0.64
    WithIOException
    0.60
    Jeografia
    0.59
     quæ
    0.58
    Diweddarwch
    0.58
    Activations Density 0.891%

    No Known Activations