© 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. 42696
    Prev
    Next
    INDEX
    Explanations

    disclaimer, sequel, plots

    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
    ici
    -0.48
     apar
    -0.47
    icia
    -0.47
    */
    -0.46
    勾
    -0.46
     rid
    -0.45
    SupportActionBar
    -0.44
    }}}}
    -0.44
    Tomorrow
    -0.43
    hbox
    -0.43
    POSITIVE LOGITS
     AssemblyCulture
    0.74
    сылкі
    0.71
    IndentedString
    0.67
    polation
    0.64
    ifications
    0.63
     estekak
    0.61
    oids
    0.60
    tagHelperRunner
    0.60
    eiro
    0.59
    ement
    0.59
    Activations Density 1.705%

    No Known Activations