© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 197
    Prev
    Next
    INDEX
    Explanations

    words and phrases expressing opinions and agreement in a discourse.

    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
    rawDesc
    -0.73
     nakalista
    -0.65
    CardModule
    -0.63
     surla
    -0.58
     Audiodateien
    -0.58
    enumi
    -0.56
    StructEnd
    -0.55
     versehen
    -0.53
    kloped
    -0.52
    IonicModule
    -0.52
    POSITIVE LOGITS
     with
    3.25
     avec
    2.45
    with
    2.41
     dengan
    2.20
     với
    2.13
     WITH
    2.11
    With
    2.00
     With
    2.00
    avec
    1.77
     עם
    1.67
    Activations Density 2.588%

    No Known Activations