© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 1307
    Prev
    Next
    INDEX
    Explanations

    the word "without"

    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
     AssemblyCulture
    -0.50
    ]='\
    -0.44
    aré
    -0.43
    urf
    -0.43
    ểm
    -0.43
    THINGS
    -0.41
    /***/
    -0.41
     bienvenue
    -0.40
    taines
    -0.40
    ეთ
    -0.38
    POSITIVE LOGITS
     regard
    0.98
     any
    0.95
    regard
    0.93
    ArrowToggle
    0.84
     resorting
    0.83
     interruption
    0.81
     knowing
    0.80
     qualquer
    0.79
     needing
    0.79
     REGARD
    0.78
    Activations Density 0.229%

    No Known Activations