© 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. 3008
    Prev
    Next
    INDEX
    Explanations

    Code, copyright, folding

    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
    ніципалі
    -0.63
    хьтан
    -0.54
    oa̍t
    -0.52
    Jîn
    -0.51
     дописавши
    -0.50
    passo
    -0.47
    Expose
    -0.47
    Erstellt
    -0.46
     corners
    -0.46
    tahui
    -0.46
    POSITIVE LOGITS
     Roskov
    0.69
    ScopeManager
    0.64
    ché
    0.55
     Hins
    0.54
    itale
    0.54
    dna
    0.52
    uestamente
    0.52
    @$
    0.52
    tagHelper
    0.51
    AGEN
    0.51
    Activations Density 0.010%

    No Known Activations