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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 94280
    Prev
    Next
    INDEX
    Explanations

    port or IP

    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
     
    -0.48
     returned
    -0.46
     M
    -0.46
     T
    -0.43
    WebElementEntity
    -0.42
     return
    -0.41
     üzere
    -0.40
     declared
    -0.39
    hut
    -0.38
    ột
    -0.38
    POSITIVE LOGITS
     itſelf
    1.05
     myſelf
    1.02
    BufferException
    0.96
    ſelves
    0.92
     themſelves
    0.92
     himſelf
    0.89
    ſelf
    0.89
     Theſe
    0.88
     AssemblyTitle
    0.87
    Hozzáférés
    0.83
    Activations Density 0.666%

    No Known Activations