© 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. 2464
    Prev
    Next
    INDEX
    Explanations

    doing

    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
     so
    -0.60
     as
    -0.57
     not
    -0.51
     on
    -0.50
     –
    -0.49
     in
    -0.49
     was
    -0.49
     —
    -0.47
     normally
    -0.46
     along
    -0.45
    POSITIVE LOGITS
    AccessorTable
    0.79
    Personensuche
    0.76
    mybatisplus
    0.75
    DockStyle
    0.75
    AndEndTag
    0.69
    bootstrapcdn
    0.68
     utafitiHapana
    0.66
    NameInMap
    0.65
    ]")]
    0.63
     يتيمه
    0.62
    Activations Density 0.005%

    No Known Activations