© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 73718
    Prev
    Next
    INDEX
    Explanations

    :

    np_max-act-logits · 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
    Datuak
    -0.88
    rungsseite
    -0.58
    érape
    -0.52
    WireFormatLite
    -0.46
     Yam
    -0.46
     TestBed
    -0.45
     Akismet
    -0.45
     viewDidLoad
    -0.45
    ASF
    -0.44
     IndexPath
    -0.44
    POSITIVE LOGITS
    importanza
    0.57
    UFACT
    0.57
     ddelweddau
    0.56
    erker
    0.56
    AndEndTag
    0.55
     compter
    0.55
    conceito
    0.54
    getSeconds
    0.53
     tartalomajánló
    0.53
    voorbeeld
    0.53
    Activations Density 0.019%

    No Known Activations