© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 17403
    Prev
    Next
    INDEX
    Explanations

    specific error messages or indications related to coding or programming issues

    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
     dangerous
    -0.52
     unsafe
    -0.50
     Yü
    -0.50
    ScopeManager
    -0.44
     olsa
    -0.42
    winston
    -0.42
     EGL
    -0.41
     déc
    -0.40
     Pier
    -0.40
    xml
    -0.40
    POSITIVE LOGITS
    PreferredItem
    1.02
     resourceCulture
    0.85
    دانشنامهٔ
    0.83
    ंदीखरीदारी
    0.81
     المعيارى
    0.79
    SequentialGroup
    0.77
     виправивши
    0.74
     &___
    0.73
    }))
    0.72
    évaluateur
    0.71
    Activations Density 0.022%

    No Known Activations