Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74286
    Prev
    Next
    INDEX
    Explanations

    Code/technical documentation

    np_max-act-logits · 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
    createServer
    -0.66
     Parac
    -0.63
    posables
    -0.62
     privée
    -0.61
    })$}
    -0.59
     Scales
    -0.59
     télévisée
    -0.59
    KELEY
    -0.58
    Reversed
    -0.57
    енча
    -0.57
    POSITIVE LOGITS
     snippetHide
    0.52
    KommentareTeilen
    0.51
    Референце
    0.41
    RequestDto
    0.41
    InjectAttribute
    0.40
     Mail
    0.39
    gun
    0.39
    guió
    0.39
    المناصب
    0.38
    Mail
    0.38
    Activations Density 0.004%

    No Known Activations