© 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. 24-RES-MATRYOSHKA-DC
    7. 139
    Prev
    Next
    INDEX
    Explanations

    the word "a" followed by an adjective modifying a noun

    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.24.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.24.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
     quæ
    -0.58
     raiſ
    -0.58
     ejus
    -0.57
     ſtate
    -0.57
    ährlich
    -0.57
     survie
    -0.54
     myſelf
    -0.53
     purpoſe
    -0.52
     charité
    -0.52
     chofe
    -0.52
    POSITIVE LOGITS
     bit
    1.02
     couple
    0.94
     lot
    0.89
     little
    0.88
     few
    0.85
     ton
    0.70
     huge
    0.69
     lotta
    0.69
     moment
    0.67
     wee
    0.67
    Activations Density 1.458%

    No Known Activations