© 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. 14558
    Prev
    Next
    INDEX
    Explanations

    assertions and claims regarding potential outcomes and expectations

    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
     متعلقه
    -0.85
     للمعارف
    -0.82
    contentLoaded
    -0.74
    GOTREF
    -0.71
     ErrIntOverflow
    -0.70
    CodeAttribute
    -0.68
     ProtoMessage
    -0.68
     समीक्षाओं
    -0.68
    原始内容存档于
    -0.66
     שוליים
    -0.66
    POSITIVE LOGITS
    peli
    0.44
    obium
    0.42
     pref
    0.42
     Devil
    0.42
     */}
    0.42
    Cura
    0.41
    据
    0.41
    gered
    0.40
    thâu
    0.40
     labi
    0.40
    Activations Density 0.240%

    No Known Activations