© 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. 4-CLT-HP
    7. 4336
    Prev
    Next
    INDEX
    Explanations

    of

    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
    SBATCH
    -0.62
     autorytatywna
    -0.55
     NUKAT
    -0.54
    getNome
    -0.51
    })*/
    -0.50
    lapsingToolbar
    -0.50
    ⓧ
    -0.49
    IsContent
    -0.48
    olesale
    -0.48
    tinyos
    -0.48
    POSITIVE LOGITS
     the
    1.24
     a
    0.85
     this
    0.75
     an
    0.74
     one
    0.71
    AddHtmlAttribute
    0.64
     some
    0.59
     Audiodateien
    0.55
    bootstrapcdn
    0.54
    prototype
    0.52
    Activations Density 0.006%

    No Known Activations