© 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. 2420
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "too" and words that are similar to "too."

    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
     very
    -0.69
     drôle
    -0.58
     with
    -0.58
     simple
    -0.55
     simpler
    -0.54
    sterious
    -0.54
    atyw
    -0.54
     interesting
    -0.53
     modest
    -0.53
     relatively
    -0.53
    POSITIVE LOGITS
    RenderAtEndOf
    0.66
    ChromeDriver
    0.61
    ConstraintMaker
    0.59
    suddenly
    0.57
    μφωνα
    0.57
     routinely
    0.56
    soon
    0.55
    aterally
    0.54
    出版年
    0.54
     '{@
    0.54
    Activations Density 0.138%

    No Known Activations