© 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. 26124
    Prev
    Next
    INDEX
    Explanations

    elements related to specific categories or classifications, particularly in arts and academic contexts

    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
    featureID
    -1.10
     Normdatei
    -0.93
    EDEFAULT
    -0.84
    存于互联网档案馆
    -0.83
     kaarangay
    -0.82
    GenerationType
    -0.82
    styleType
    -0.82
    AnchorStyles
    -0.81
     AssemblyCulture
    -0.80
    ]")]
    -0.80
    POSITIVE LOGITS
    hogy
    0.45
    input
    0.42
    ồm
    0.42
     mówią
    0.42
    joi
    0.40
     stay
    0.40
     Jove
    0.40
    AYE
    0.39
     Ovid
    0.39
     forged
    0.39
    Activations Density 0.565%

    No Known Activations