© 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. 22-RES-MATRYOSHKA-DC
    7. 1993
    Prev
    Next
    INDEX
    Explanations

    code-related keywords such as public, private, new, static, etc

    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.22.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.22.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
    te
    -0.46
    al
    -0.45
     od
    -0.45
    vi
    -0.42
    ur
    -0.42
    テ
    -0.42
    us
    -0.42
    at
    -0.42
    q
    -0.41
    č
    -0.41
    POSITIVE LOGITS
     String
    1.01
    Datuak
    0.95
    prefixer
    0.91
    String
    0.86
     Normdatei
    0.85
     boolean
    0.85
     يتيمه
    0.84
     string
    0.84
     Audiodateien
    0.84
    
    0.83
    Activations Density 0.415%

    No Known Activations