© 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. 12-RES-MATRYOSHKA-DC
    7. 20817
    Prev
    Next
    INDEX
    Explanations

    the word "while" and its variants

    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
     TON
    -0.46
    en
    -0.44
    NameInMap
    -0.44
    BigInteger
    -0.43
     Wolfe
    -0.42
     mors
    -0.41
    liche
    -0.41
     rady
    -0.40
    ്ട
    -0.40
    gent
    -0.40
    POSITIVE LOGITS
    RenderAtEndOf
    1.04
    SOUNDBITE
    0.90
     للمعارف
    0.85
    UrlResolution
    0.85
    MENAFN
    0.84
    principalColumn
    0.79
    InstanceState
    0.78
     wikipagina
    0.78
    endregion
    0.77
    发表于
    0.77
    Activations Density 0.018%

    No Known Activations