© 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. 935
    Prev
    Next
    INDEX
    Explanations

    LaTeX math mode equations

    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
     —
    -0.99
    })^
    -0.98
    }}^
    -0.91
    )^
    -0.89
    |^
    -0.84
    ]^
    -0.83
     nggak
    -0.81
    |_
    -0.80
    ))^
    -0.79
    }}_
    -0.76
    POSITIVE LOGITS
     �
    0.81
    _{
    0.76
     _{
    0.76
     ${{
    0.75
    ^{*}\
    0.74
    �
    0.74
     $_{
    0.73
    left
    0.71
    ^{
    0.70
    <u>
    0.69
    Activations Density 2.827%

    No Known Activations