© 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. 2828
    Prev
    Next
    INDEX
    Explanations

    string manipulation functions and file handling, often in the context of code.

    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
     विश्वसनीयता
    -0.50
     ausz
    -0.44
     virtuel
    -0.43
    arien
    -0.43
     oble
    -0.41
     aberta
    -0.41
     gå
    -0.40
    웃
    -0.40
    (&:
    -0.40
    avir
    -0.39
    POSITIVE LOGITS
     split
    0.85
    MigrationBuilder
    0.83
     AttributeSet
    0.81
    split
    0.79
     substring
    0.78
     StringTokenizer
    0.78
     replace
    0.75
     trim
    0.74
     Split
    0.73
     trimming
    0.73
    Activations Density 0.167%

    No Known Activations