© 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. 400
    Prev
    Next
    INDEX
    Explanations

    instances where someone is describing other's character or actions, or providing a definition/description of something

    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
    findpost
    -0.95
    تقاوى
    -0.70
     disambiguazione
    -0.66
    AndEndTag
    -0.64
    !*\
    -0.59
    kenstock
    -0.58
     AssemblyCompany
    -0.58
    évaluateur
    -0.56
    LookAnd
    -0.53
    MessageOf
    -0.52
    POSITIVE LOGITS
     as
    2.59
     sebagai
    1.98
     jako
    1.59
     ως
    1.46
     Sebagai
    1.38
    sebagai
    1.31
     как
    1.30
    作为
    1.29
     као
    1.27
     comme
    1.25
    Activations Density 2.793%

    No Known Activations