© 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. 26733
    Prev
    Next
    INDEX
    Explanations

    phrases describing significant effects or changes

    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
     not
    -0.54
     open
    -0.49
     experience
    -0.48
     Horst
    -0.47
    </em>
    -0.46
    })));
    -0.45
     rest
    -0.45
     mus
    -0.44
     red
    -0.44
     re
    -0.44
    POSITIVE LOGITS
    effect
    1.02
     Effects
    0.97
    effects
    0.96
     effect
    0.96
     Effect
    0.92
    Effects
    0.91
     effects
    0.90
     EFFECTS
    0.89
     EFFECT
    0.87
    脚注の使い方
    0.84
    Activations Density 0.047%

    No Known Activations