© 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. 22-RES-MATRYOSHKA-DC
    7. 1807
    Prev
    Next
    INDEX
    Explanations

    superlatives (words like best, largest, greatest) and related words.

    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.22.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.22.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
     iprot
    -0.60
    躇
    -0.59
     tfsi
    -0.58
     disambiguazione
    -0.58
    ertale
    -0.57
    kant
    -0.56
    alakip
    -0.55
    Various
    -0.54
    bral
    -0.54
    quels
    -0.54
    POSITIVE LOGITS
     ever
    2.25
     EVER
    1.78
    ever
    1.66
    Ever
    1.49
     Ever
    1.41
     jemals
    1.36
    EVER
    1.35
     jamás
    1.34
     ooit
    1.31
     possible
    1.25
    Activations Density 1.080%

    No Known Activations