© 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. 2550
    Prev
    Next
    INDEX
    Explanations

    angle brackets

    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
     Mr
    -0.68
    tvguidetime
    -0.66
    PostMapping
    -0.63
    aarrggbb
    -0.58
    mappedBy
    -0.58
    findOneAndUpdate
    -0.58
     d
    -0.56
     w
    -0.55
    ന്റെ
    -0.55
     y
    -0.54
    POSITIVE LOGITS
    \<^
    0.84
     Diſ
    0.82
     purpoſe
    0.82
     diſt
    0.81
     Majefty
    0.81
    ſelf
    0.81
     pleaſure
    0.79
    ſelves
    0.79
     itſelf
    0.77
     greateſt
    0.77
    Activations Density 0.010%

    No Known Activations