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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 19429
    Prev
    Next
    INDEX
    Explanations

    numeric ranges in data reporting

    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
     OnTrigger
    -0.62
     BigNumberish
    -0.58
     colorWith
    -0.55
     Signalez
    -0.55
    ñora
    -0.54
    anmoins
    -0.53
    marginVertical
    -0.52
     betweenstory
    -0.51
     occaf
    -0.50
    PreferredItem
    -0.50
    POSITIVE LOGITS
    principalTable
    0.84
    setVerticalGroup
    0.73
     AssemblyTitle
    0.65
    LookAnd
    0.60
    AccessorTable
    0.60
    msgTypes
    0.58
    errHandler
    0.58
    plona
    0.57
     oprot
    0.56
     industry
    0.56
    Activations Density 0.004%

    No Known Activations