© 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. 24491
    Prev
    Next
    INDEX
    Explanations

    suggestions or recommendations for improvement or modification

    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
     consider
    -0.54
    ang
    -0.49
     instead
    -0.49
    <em>
    -0.47
     wrong
    -0.47
     invece
    -0.47
     rather
    -0.46
    الإنجليزية
    -0.46
    thansa
    -0.44
    tanooga
    -0.43
    POSITIVE LOGITS
    HostException
    0.82
     AssemblyVersion
    0.76
    Réponse
    0.76
    </thead>
    0.75
    LEncoder
    0.75
    ContentAlignment
    0.73
    SBATCH
    0.71
    etah
    0.69
    theore
    0.68
    Personendaten
    0.68
    Activations Density 0.030%

    No Known Activations