© 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. 18547
    Prev
    Next
    INDEX
    Explanations

    references to unsafe memory management concepts in programming

    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
    ьажоргаш
    -0.67
    []>(
    -0.61
     Lain
    -0.59
    AndEndTag
    -0.59
    lay
    -0.59
    eger
    -0.59
     PropTypes
    -0.58
    jspx
    -0.58
     Laing
    -0.58
    alaya
    -0.58
    POSITIVE LOGITS
    unsafe
    1.05
     disambiguazione
    0.71
     unsafe
    0.70
     سكانية
    0.68
    ])).
    0.67
    Knox
    0.65
    ])):
    0.64
    })]
    0.63
    ckle
    0.63
    ]})
    0.63
    Activations Density 0.001%

    No Known Activations