© 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. 3088
    Prev
    Next
    INDEX
    Explanations

    -

    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
     Eſ
    -0.69
     raiſ
    -0.66
     eſ
    -0.63
     pleaſure
    -0.63
     ſtill
    -0.60
     Jefus
    -0.59
     ſhould
    -0.59
     itſelf
    -0.59
     diſt
    -0.59
    Putting
    -0.59
    POSITIVE LOGITS
    QMetaType
    0.51
     AssemblyProduct
    0.45
    ########.
    0.45
     Rosen
    0.44
    肥
    0.43
    ̣t
    0.41
     AB
    0.41
     Rose
    0.40
     Code
    0.40
    XmlAccessType
    0.39
    Activations Density 0.004%

    No Known Activations