© 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. 22-RES-MATRYOSHKA-DC
    7. 3301
    Prev
    Next
    INDEX
    Explanations

    phrases related to spiritual openness or possibility

    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
    Negative Logits
    twimg
    -0.63
     Monfieur
    -0.60
    adpleegd
    -0.60
    Παραπομπές
    -0.59
    Portail
    -0.59
     Theſe
    -0.57
    Примечания
    -0.57
    AttributeSet
    -0.56
    terno
    -0.55
     Efq
    -0.54
    POSITIVE LOGITS
     space
    2.91
    space
    2.47
     Space
    2.34
    Space
    2.30
     SPACE
    2.22
     espacio
    2.20
    SPACE
    2.06
     espaço
    2.03
    空间
    1.96
     spaces
    1.95
    Activations Density 0.415%

    No Known Activations