© 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. 94586
    Prev
    Next
    INDEX
    Explanations

    praises

    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
    -0.91
     виправивши
    -0.89
    LookAnd
    -0.81
     Мексичка
    -0.75
    RenderAtEndOf
    -0.72
    SequentialGroup
    -0.69
    uxxxx
    -0.68
     }}"></
    -0.67
    WebElementEntity
    -0.67
     transfieras
    -0.66
    POSITIVE LOGITS
     as
    0.82
     tirelessly
    0.44
     endlessly
    0.42
     createSlice
    0.40
     WaitForSeconds
    0.40
    labelledby
    0.39
     fever
    0.38
     by
    0.38
     migh
    0.37
    SaveChangesAsync
    0.37
    Activations Density 0.001%

    No Known Activations