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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 44306
    Prev
    Next
    INDEX
    Explanations

    Estimated, MH

    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
     estimated
    -1.07
    Estimated
    -1.07
    estimated
    -1.06
     Estimated
    -0.97
    Erreferentziak
    -0.85
     كومونز
    -0.84
    EndGlobalSection
    -0.79
    +#+
    -0.77
    SourceChecksum
    -0.77
    ########.
    -0.77
    POSITIVE LOGITS
     metav
    0.59
    IGENCE
    0.51
     vulgares
    0.48
    TabLayout
    0.46
     EGR
    0.45
    Intent
    0.45
    edu
    0.45
    AddressBook
    0.44
     Kildare
    0.44
     appraisal
    0.44
    Activations Density 0.333%

    No Known Activations