© 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. 27100
    Prev
    Next
    INDEX
    Explanations

    phrases indicating hypocrisy and obstruction in political discourse

    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
    LabelTagHelper
    -0.65
    ReusableCell
    -0.63
    DebuggerNonUser
    -0.59
    出版年
    -0.59
    numerusform
    -0.58
    RenderAtEndOf
    -0.58
    IUrlHelper
    -0.56
    AndroidJUnit
    -0.56
     ſte
    -0.56
     myſelf
    -0.56
    POSITIVE LOGITS
    LABEL
    0.49
    gazette
    0.44
     flexing
    0.44
    Draft
    0.44
    acherous
    0.43
    ActivityCompat
    0.43
    TryParse
    0.43
    mybatisplus
    0.42
     defaultstate
    0.42
     flex
    0.42
    Activations Density 0.170%

    No Known Activations