© 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. 16118
    Prev
    Next
    INDEX
    Explanations

    statements regarding assertions or claims

    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
    IContainer
    -0.73
    EndContext
    -0.65
     disambiguazione
    -0.65
    ISupport
    -0.62
    knex
    -0.62
    invokeLater
    -0.58
    chastic
    -0.57
     OnInit
    -0.57
    AddColumn
    -0.57
    entrySet
    -0.55
    POSITIVE LOGITS
     claimed
    0.81
     claiming
    0.78
     claims
    0.69
     claim
    0.68
    claim
    0.66
    claimed
    0.65
     Claim
    0.65
    claims
    0.63
     prétend
    0.62
     purport
    0.61
    Activations Density 0.060%

    No Known Activations