© 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. 18-RES-MATRYOSHKA-DC
    7. 1093
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns or references

    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.18.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.18.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
     thought
    -0.67
     thinks
    -0.67
     your
    -0.63
     think
    -0.62
     nghĩ
    -0.59
     thinking
    -0.56
     thoughts
    -0.56
    Hoping
    -0.54
    thought
    -0.53
    Thought
    -0.53
    POSITIVE LOGITS
    SequentialGroup
    0.88
     EnglishChoose
    0.82
     فريبيس
    0.75
     mustn
    0.75
     sbag
    0.73
     should
    0.72
    should
    0.71
     needn
    0.68
     incorrectly
    0.67
     صوتيه
    0.67
    Activations Density 0.772%

    No Known Activations