© 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. 4-CLT-HP
    7. 408
    Prev
    Next
    INDEX
    Explanations

    pins

    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
     disambiguazione
    -0.95
    InputBorder
    -0.75
    +#+
    -0.73
     AssemblyCulture
    -0.71
     kasarigan
    -0.70
    DebuggerNonUser
    -0.69
    Tikang
    -0.69
    StructEnd
    -0.68
     EconPapers
    -0.66
     متعلقه
    -0.64
    POSITIVE LOGITS
     it
    0.63
     altogether
    0.53
     zelve
    0.49
     esso
    0.49
     while
    0.49
     Gesamt
    0.48
     ciasc
    0.48
    It
    0.47
     proprement
    0.47
     whilst
    0.43
    Activations Density 0.008%

    No Known Activations