© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 40648
    Prev
    Next
    INDEX
    Explanations

    ghan

    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
    parsedMessage
    -0.75
    LookAnd
    -0.73
    })));
    -0.73
     Bestimm
    -0.71
     FILL
    -0.70
     €)
    -0.69
     fill
    -0.68
     fills
    -0.68
     '\\;'
    -0.68
     resourceCulture
    -0.65
    POSITIVE LOGITS
    say
    0.48
     InputDecoration
    0.47
    målet
    0.44
    shar
    0.44
     ब्रेकडाउन
    0.43
    sa
    0.42
    sie
    0.42
    sockets
    0.41
    says
    0.40
    INCREF
    0.40
    Activations Density 0.113%

    No Known Activations