© 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. 12-RES-MATRYOSHKA-DC
    7. 9585
    Prev
    Next
    INDEX
    Explanations

    numerical values or figures in various formats

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
     Oblig
    -0.66
    opic
    -0.66
    atomy
    -0.61
    AILABLE
    -0.61
    DebuggerNonUser
    -0.60
    jude
    -0.59
    raff
    -0.59
    psia
    -0.58
    qiao
    -0.58
     Calla
    -0.57
    POSITIVE LOGITS
    Hozzáférés
    0.75
     setuptools
    0.74
     mxArray
    0.69
     Meksiku
    0.65
     GenerationType
    0.65
    المناصب
    0.61
    WindowConstants
    0.60
    /**
    0.60
    جوايز
    0.60
    monary
    0.59
    Activations Density 0.004%

    No Known Activations