© 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. 2293
    Prev
    Next
    INDEX
    Explanations

    angle brackets, especially closing angle brackets followed by short strings

    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
    Décès
    -0.51
     useHistory
    -0.50
    իվ
    -0.48
    lık
    -0.48
    table
    -0.47
    lighed
    -0.46
    存于互联网档案馆
    -0.45
    strong
    -0.44
     betweenstory
    -0.44
    fulness
    -0.44
    POSITIVE LOGITS
    +#+#
    0.95
     tartalomajánló
    0.88
    تقاوى
    0.88
    RegressionTest
    0.85
    ReusableCell
    0.79
     виправивши
    0.79
    KURZBESCHREIBUNG
    0.75
     متعلقه
    0.75
     &___
    0.72
    AutoScaleMode
    0.70
    Activations Density 0.070%

    No Known Activations