© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-RES-MATRYOSHKA-DC
    7. 1477
    Prev
    Next
    INDEX
    Explanations

    gibberish with numbers, punctuation and the letters 'L', 'c', 'M', 'z', 'v', 'l', or 'h'

    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
    Negative Logits
     *}
    -0.73
    #}
    -0.67
     الحره
    -0.66
    تقاوى
    -0.64
    **:
    -0.64
     *}$
    -0.63
     *
    -0.62
    **,
    -0.61
     :
    -0.60
     محفوظة
    -0.60
    POSITIVE LOGITS
    V
    0.66
     
    0.58
    Q
    0.56
    L
    0.55
    v
    0.54
    H
    0.50
    q
    0.48
    l
    0.46
    oplasma
    0.45
     aikaa
    0.44
    Activations Density 0.069%

    No Known Activations