© 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. 1-CLT-HP
    7. 12302
    Prev
    Next
    INDEX
    Explanations

    examine

    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
    modb
    -0.65
    <bos>
    -0.62
    +:+
    -0.60
     мѣ
    -0.54
    XmlAccessType
    -0.54
    bollah
    -0.53
    ädie
    -0.53
     AssemblyCulture
    -0.53
    crollView
    -0.53
    PreAuthorize
    -0.52
    POSITIVE LOGITS
     restrictive
    0.55
    ])));
    0.54
    '])->
    0.52
     royalties
    0.51
     sien
    0.49
     Гото
    0.49
     faithfulness
    0.47
     Respon
    0.47
    ')).
    0.47
     entitlements
    0.46
    Activations Density 0.007%

    No Known Activations