© 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. 5-CLT-HP
    7. 2613
    Prev
    Next
    INDEX
    Explanations

    questions/informational content

    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
    TypeMap
    -0.45
    omin
    -0.42
    messageInfo
    -0.41
     Olímp
    -0.41
    KURZBESCHREIBUNG
    -0.40
    SIZ
    -0.39
     numbness
    -0.38
    :][
    -0.38
     hyperplasia
    -0.37
     tachy
    -0.37
    POSITIVE LOGITS
    :✨
    0.87
     CURLOPT
    0.75
     Starts
    0.70
     deserve
    0.68
     Requires
    0.68
     TestBed
    0.68
     starts
    0.68
     requires
    0.66
    }))
    0.66
     deserves
    0.65
    Activations Density 0.000%

    No Known Activations