© 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. 71
    Prev
    Next
    INDEX
    Explanations

    personal anecdotes, often containing details about daily life events or emotions.

    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
     avoient
    -0.98
     ainfi
    -0.98
     étoient
    -0.98
     plufieurs
    -0.96
     iſt
    -0.95
     auroit
    -0.94
     feroit
    -0.93
     sahiptir
    -0.92
     ſind
    -0.90
    <bos>
    -0.89
    POSITIVE LOGITS
    !
    1.60
    !!
    1.28
    …
    1.27
    !!!
    1.25
    ...
    1.18
     anyway
    1.16
    !!!!
    1.14
     :)
    1.13
    ,
    1.13
     right
    1.12
    Activations Density 9.582%

    No Known Activations