© 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. 1266
    Prev
    Next
    INDEX
    Explanations

    parenthesized years or months, adjectives of nationality, and sports

    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
    intenant
    -0.56
     entanto
    -0.51
    ποτε
    -0.49
     capitolo
    -0.49
     frattempo
    -0.48
     medesimo
    -0.48
    AnimationsModule
    -0.47
     person
    -0.47
     indivíduo
    -0.47
    ilhas
    -0.46
    POSITIVE LOGITS
    rungsseite
    0.81
    ंदीखरीदारी
    0.69
     composer
    0.66
     mergeFrom
    0.66
     setuptools
    0.65
     economist
    0.65
     المعيارى
    0.65
    Composer
    0.63
     film
    0.62
     novelist
    0.62
    Activations Density 0.312%

    No Known Activations