© 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. 22-RES-MATRYOSHKA-DC
    7. 2875
    Prev
    Next
    INDEX
    Explanations

    the word "every"

    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
     of
    -1.09
     AssemblyCompany
    -0.79
     numberWith
    -0.56
    CloseOperation
    -0.56
     Wikimédia
    -0.52
     của
    -0.52
    fromCharCode
    -0.52
    terase
    -0.51
     and
    -0.49
    makeText
    -0.48
    POSITIVE LOGITS
     single
    1.36
    single
    1.23
    Single
    1.14
     Single
    1.11
     SINGLE
    1.09
    every
    1.08
     poffible
    1.01
     every
    0.93
    TagHelper
    0.93
    SINGLE
    0.92
    Activations Density 0.048%

    No Known Activations