© 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. 30280
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conditions or situations that might lead to negative outcomes

    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
     consultato
    -0.92
     autorytatywna
    -0.89
     mergeFrom
    -0.84
    JspWriter
    -0.80
     насељу
    -0.79
     <<<<<<<<<<<<<<
    -0.75
     typelib
    -0.75
     الاطلاع
    -0.74
    ModelSerializer
    -0.73
    PerformLayout
    -0.71
    POSITIVE LOGITS
    QtWidgets
    0.47
     sztu
    0.45
    achet
    0.44
     aikaa
    0.44
    뀜
    0.44
    طلاق
    0.44
    XtraEditors
    0.43
     πέ
    0.41
     rozwo
    0.41
    LBL
    0.40
    Activations Density 0.098%

    No Known Activations