© 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. 96367
    Prev
    Next
    INDEX
    Explanations

    ImageView

    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
    <bos>
    -0.80
     NDEBUG
    -0.69
     Efq
    -0.68
     raiſ
    -0.62
     Jefus
    -0.61
    Clik
    -0.61
     Majefty
    -0.60
    Descriere
    -0.58
     ſever
    -0.57
    Pronunciation
    -0.57
    POSITIVE LOGITS
    principalTable
    0.54
     CWE
    0.46
    pell
    0.42
    PEAT
    0.42
    engue
    0.42
    mania
    0.41
     emel
    0.41
    gran
    0.40
    ấm
    0.40
    Mucha
    0.40
    Activations Density 0.001%

    No Known Activations