© 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. 29794
    Prev
    Next
    INDEX
    Explanations

    expressions of dissatisfaction or inadequacy in communication

    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
    jsonwebtoken
    -0.60
    RTEX
    -0.57
     récents
    -0.57
    jspb
    -0.56
     omge
    -0.54
     Juris
    -0.53
    новништво
    -0.53
     chiare
    -0.53
     initComponents
    -0.52
    Lew
    -0.52
    POSITIVE LOGITS
     describe
    0.79
     adjectives
    0.76
     indescribable
    0.73
     Describe
    0.69
     descri
    0.68
     describing
    0.67
     décrire
    0.65
     description
    0.65
     descriptions
    0.63
     توص
    0.63
    Activations Density 0.066%

    No Known Activations