© 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. 15706
    Prev
    Next
    INDEX
    Explanations

    metrics and scales related to clinical assessments or studies

    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
    Negative Logits
     OnTriggerEnter
    -0.53
     nhiên
    -0.52
     الدولى
    -0.51
    AddHtmlAttribute
    -0.49
     virginity
    -0.49
     deducted
    -0.48
     Philo
    -0.48
    ngOnInit
    -0.47
     svolta
    -0.47
     assolu
    -0.47
    POSITIVE LOGITS
    Jegyzetek
    0.59
     MethodInfo
    0.56
    ″]
    0.56
    ieważ
    0.55
    μως
    0.55
    مصادر
    0.53
    FailureListener
    0.53
     insuffisamment
    0.52
    ursos
    0.51
     recevez
    0.50
    Activations Density 0.020%

    No Known Activations