© 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. 12036
    Prev
    Next
    INDEX
    Explanations

    terms that indicate negativity or disapproval in a context

    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
    WireFormatLite
    -0.57
    windowFixed
    -0.55
    raulic
    -0.49
     سكانية
    -0.47
     Holliday
    -0.46
    InputTagHelper
    -0.46
    iano
    -0.45
    حياته
    -0.43
     sign
    -0.43
     Anyways
    -0.43
    POSITIVE LOGITS
    AppMethodBeat
    1.06
    PhysRevD
    0.90
    .*")]
    0.72
    findpost
    0.66
    Portale
    0.62
    .",
    0.61
    apnews
    0.61
     ModelExpression
    0.60
    AnimationsModule
    0.58
    Портал
    0.57
    Activations Density 0.000%

    No Known Activations