© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 22726
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate effective communication and manipulation

    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
     Efq
    -0.88
    ⓧ
    -0.88
    دانشنامهٔ
    -0.82
    Datuak
    -0.79
    ImageContext
    -0.78
     linkovi
    -0.75
     cherchés
    -0.74
    __(/*!
    -0.74
     متعلقه
    -0.71
    StructEnd
    -0.71
    POSITIVE LOGITS
    edb
    0.47
    好不容易
    0.45
     b
    0.44
     throw
    0.40
    Stepping
    0.40
    izowane
    0.40
    ORMAL
    0.40
     rare
    0.39
    难得
    0.39
     understandably
    0.39
    Activations Density 0.139%

    No Known Activations