© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 14728
    Prev
    Next
    INDEX
    Explanations

    emotional expressions and sentiments

    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
    ClCompile
    -0.60
    //
    -0.56
    yarnpkg
    -0.52
     Dernière
    -0.52
    Eloquent
    -0.52
     bada
    -0.52
     незавершена
    -0.51
    __':
    -0.51
    rawd
    -0.50
    ximadamente
    -0.50
    POSITIVE LOGITS
    providedIn
    0.67
    Tikang
    0.62
     Somehow
    0.59
    "}")
    0.58
     somehow
    0.57
     Danville
    0.55
    ellees
    0.54
    complexContent
    0.54
    脚注の使い方
    0.52
    žku
    0.52
    Activations Density 0.003%

    No Known Activations