© 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. 18-RES-MATRYOSHKA-DC
    7. 810
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to behavior and how things are done

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.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
    ⓧ
    -0.70
    ftagPool
    -0.66
     Meksiku
    -0.65
    ArrowToggle
    -0.64
    MessageState
    -0.60
     atteinte
    -0.60
     NSCoder
    -0.59
    ietal
    -0.58
     neceffary
    -0.58
     Perfon
    -0.57
    POSITIVE LOGITS
     way
    1.46
     manner
    1.34
     ways
    1.13
     WAY
    1.13
     differently
    1.12
    Way
    1.11
     Way
    1.09
     manière
    1.08
    way
    1.05
    manner
    1.03
    Activations Density 1.032%

    No Known Activations