© 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. 638
    Prev
    Next
    INDEX
    Explanations

    the word "special" followed by other relatively common words

    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
    moso
    -0.55
    mosa
    -0.54
    eadas
    -0.53
    ển
    -0.51
     comprim
    -0.48
    TestBase
    -0.47
    Portale
    -0.47
    曖昧さ回避
    -0.46
    antwoorden
    -0.46
    نده
    -0.46
    POSITIVE LOGITS
     particolare
    0.74
    /**
    0.73
     particulares
    0.73
    出版年
    0.73
    Particular
    0.71
    SPECIAL
    0.70
    specific
    0.70
     special
    0.70
     Particular
    0.69
    Życiorys
    0.69
    Activations Density 0.540%

    No Known Activations