© 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. 124
    Prev
    Next
    INDEX
    Explanations

    the word "and"

    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
     Efq
    -1.33
     Shakspeare
    -1.19
     itſelf
    -1.17
     Majefty
    -1.16
     himſelf
    -1.14
     Jefus
    -1.09
     myſelf
    -1.09
     themſelves
    -1.06
     Cæsar
    -1.05
     Chriftian
    -1.05
    POSITIVE LOGITS
     hence
    1.29
     then
    1.21
     thus
    1.20
     therefore
    1.19
     also
    1.16
     other
    1.13
     even
    1.12
     the
    1.09
     subsequently
    1.09
     thereby
    1.05
    Activations Density 3.090%

    No Known Activations