© 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. 1165
    Prev
    Next
    INDEX
    Explanations

    the word "as."

    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
    もの
    -0.59
    getKeyCode
    -0.57
    jsoup
    -0.53
    こと
    -0.52
    ものに
    -0.48
    ことで
    -0.48
    DataAnnotations
    -0.48
    ことの
    -0.48
     становника
    -0.47
    izr
    -0.47
    POSITIVE LOGITS
     well
    1.41
     opposed
    1.21
     soon
    1.06
     follows
    1.06
     evidenced
    0.93
     far
    0.90
     shown
    0.88
     regards
    0.85
    pires
    0.84
     usual
    0.84
    Activations Density 0.759%

    No Known Activations