© 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. 1141
    Prev
    Next
    INDEX
    Explanations

    the word "access", sometimes also activating on related 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
    انيف
    -0.61
     surla
    -0.58
    udadera
    -0.58
    jamientos
    -0.57
    MigrationBuilder
    -0.56
     BQ
    -0.56
    indrome
    -0.54
    setIsLoading
    -0.53
    eterangan
    -0.53
     tanda
    -0.53
    POSITIVE LOGITS
    ACCESS
    1.05
     Access
    1.02
     ACCESS
    1.01
     access
    0.97
    access
    0.89
    Access
    0.87
     acces
    0.81
     accesses
    0.81
    Acces
    0.77
     Acces
    0.75
    Activations Density 0.140%

    No Known Activations