© 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. 32261
    Prev
    Next
    INDEX
    Explanations

    indicators of data structure definitions and database table properties

    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
     poudre
    -0.62
    __":
    -0.58
     spese
    -0.56
    __*/
    -0.56
    PhysRevD
    -0.55
    ாய
    -0.54
    ighorn
    -0.54
    存于互联网档案馆
    -0.53
     Normdatei
    -0.52
     marquées
    -0.52
    POSITIVE LOGITS
    ագրություններ
    0.63
    })();
    0.60
     defaultstate
    0.60
    PrototypeOf
    0.58
    სქოლიო
    0.58
    ExecuteReader
    0.52
    يكب
    0.52
    }();
    0.51
     bağlantılar
    0.51
    onar
    0.51
    Activations Density 0.099%

    No Known Activations