© 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. 24361
    Prev
    Next
    INDEX
    Explanations

    words and patterns associated with negative responses or failures

    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
    "]];
    -0.65
    ])));
    -0.63
    }];
    -0.54
    ])))
    -0.53
    </i>
    -0.52
    ']?>
    -0.52
     stronie
    -0.52
    कारी
    -0.51
    igel
    -0.51
     tanı
    -0.51
    POSITIVE LOGITS
    存于互联网档案馆
    0.97
     propOrder
    0.93
    ImageContext
    0.84
    PyExc
    0.83
     Normdatei
    0.82
    دانشنامهٔ
    0.82
     مشين
    0.81
     snippetHide
    0.79
     doubtnut
    0.78
    NewGuid
    0.78
    Activations Density 0.012%

    No Known Activations