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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15257
    Prev
    Next
    INDEX
    Explanations

    references to computational models or technical descriptions related to magnetic structures or simulations

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nocache
    -0.61
    SourceChecksum
    -0.60
    enderror
    -0.59
    ativistic
    -0.58
    Portale
    -0.56
    XtraReports
    -0.56
    principalColumn
    -0.56
    atiche
    -0.56
    onymous
    -0.55
     aéri
    -0.55
    POSITIVE LOGITS
    JECT
    2.88
    ject
    2.83
    jects
    2.39
    jected
    1.87
    jec
    1.82
    jections
    1.42
    jectable
    1.30
    jection
    1.22
    JECTION
    1.11
    jective
    1.00
    Activations Density 0.003%

    No Known Activations