© 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
    2. Gemma-2-2B
    3. 22-RES-MATRYOSHKA-DC
    4. 2492
    Prev
    Next
    INDEX
    Explanations

    sentences indicating an opinion or deduction, often using "must", "might", "appear", or "will"

    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
     is
    -0.62
     Wikimedijinoj
    -0.57
    دانشنامهٔ
    -0.57
    RuleContext
    -0.53
    发表于
    -0.52
     serve
    -0.52
     favourably
    -0.52
    клопе
    -0.51
    PointerException
    -0.50
    Numerology
    -0.50
    POSITIVE LOGITS
     be
    1.26
    Be
    0.95
    be
    0.95
     Be
    0.92
     BE
    0.88
     être
    0.85
    BE
    0.83
     быть
    0.82
     seja
    0.80
    MemoryWarning
    0.76
    Activations Density 0.190%

    No Known Activations