© 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. 12-RES-MATRYOSHKA-DC
    7. 18486
    Prev
    Next
    INDEX
    Explanations

    syntax associated with programming parameters and arguments in code documentation

    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
     Reichen
    -0.43
    mailto
    -0.42
    IsContent
    -0.42
    momento
    -0.42
     lighter
    -0.41
     harap
    -0.41
     momento
    -0.40
    isième
    -0.40
    ValueMap
    -0.40
    ριθ
    -0.40
    POSITIVE LOGITS
    
    1.03
    DockStyle
    0.87
     Roskov
    0.82
     onAnimation
    0.81
    ResumeLayout
    0.78
    ChildScrollView
    0.75
     WaitForSeconds
    0.75
     tartalomajánló
    0.75
     GoogleFonts
    0.71
    parsedMessage
    0.70
    Activations Density 0.010%

    No Known Activations