© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 3215
    Prev
    Next
    INDEX
    Explanations

    inventions

    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
     Normdatei
    -0.63
     propOrder
    -0.59
    Бахар
    -0.59
    ederos
    -0.59
    CompleteListener
    -0.56
     refroid
    -0.54
     يتيمه
    -0.54
    principalColumn
    -0.53
    esri
    -0.53
    AsUp
    -0.53
    POSITIVE LOGITS
     the
    0.70
     a
    0.59
     something
    0.56
     things
    0.54
     or
    0.52
     an
    0.51
     dynamic
    0.51
    Према
    0.51
     mobile
    0.50
    إنه
    0.50
    Activations Density 0.001%

    No Known Activations