© 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. 25714
    Prev
    Next
    INDEX
    Explanations

    terms related to reserved rights and permissions

    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
    MNA
    -0.70
     flèche
    -0.70
    uatan
    -0.69
    </tr>
    -0.63
    getResponse
    -0.62
     Wheatley
    -0.61
    tache
    -0.60
     rid
    -0.60
    ngths
    -0.59
    Morte
    -0.58
    POSITIVE LOGITS
     Reserve
    1.57
    RESERV
    1.48
    Reserve
    1.47
     RESERVE
    1.44
     reserve
    1.42
     Reserves
    1.40
     reserves
    1.38
     RESERV
    1.33
     Reserv
    1.26
    reserve
    1.26
    Activations Density 0.012%

    No Known Activations