© 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. 24-RES-MATRYOSHKA-DC
    7. 715
    Prev
    Next
    INDEX
    Explanations

    expressions of emotion or frustration

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.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.24.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
    UnusedPrivate
    -0.81
     дописавши
    -0.75
     للمعارف
    -0.73
    Geplaatst
    -0.72
     otomatig
    -0.72
     transfieras
    -0.71
    EndContext
    -0.69
    BeginContext
    -0.68
    RegistryLite
    -0.66
    Enllaces
    -0.66
    POSITIVE LOGITS
     greatly
    1.64
     heavily
    1.51
     immensely
    1.47
     tremendously
    1.42
     considerably
    1.38
     enormously
    1.38
     strongly
    1.30
     fortement
    1.26
     hugely
    1.23
     migh
    1.23
    Activations Density 0.986%

    No Known Activations