© 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. 5-CLT-HP
    7. 96119
    Prev
    Next
    INDEX
    Explanations

    article snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quæ
    -0.75
    Espèce
    -0.66
     pleaſure
    -0.63
     niedersachsen
    -0.62
    èdia
    -0.60
     ejus
    -0.60
     eletrônico
    -0.60
     Grèce
    -0.59
    breaking
    -0.57
    breaker
    -0.57
    POSITIVE LOGITS
     the
    0.66
    …
    0.56
    ...
    0.56
     ...
    0.48
    ….
    0.45
     …
    0.45
    ....
    0.44
    .....
    0.42
     --
    0.42
    ......
    0.42
    Activations Density 0.000%

    No Known Activations