© 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. 2244
    Prev
    Next
    INDEX
    Explanations

    code and URLs

    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
    StoryboardSegue
    -0.66
    verifyException
    -0.61
    ArrowToggle
    -0.53
     Adults
    -0.47
    ensement
    -0.44
     Blum
    -0.44
    JsonProperty
    -0.43
     adults
    -0.43
    Aiheesta
    -0.42
     Jaffe
    -0.42
    POSITIVE LOGITS
     ProtoMessage
    0.56
    domada
    0.56
    Ehrungen
    0.55
    sizeCache
    0.54
    enciaga
    0.53
     bege
    0.52
    honor
    0.50
    ответ
    0.50
    art
    0.50
     cherchés
    0.49
    Activations Density 0.004%

    No Known Activations