© 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. 17673
    Prev
    Next
    INDEX
    Explanations

    negative sentiment or adversely connotative phrases

    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
    Autoritní
    -0.60
    didSet
    -0.60
    ngdoc
    -0.57
    xFFFFFF
    -0.56
     nargin
    -0.54
    érience
    -0.54
     latest
    -0.53
     report
    -0.52
    Vía
    -0.51
    onSave
    -0.50
    POSITIVE LOGITS
     noix
    0.52
     indisponible
    0.51
    \}\\
    0.50
    ècie
    0.49
    ViewImports
    0.48
    }>;
    0.48
     beziehungs
    0.48
     chi̍t
    0.48
    __);
    0.47
    __',
    0.46
    Activations Density 0.065%

    No Known Activations