Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 3780
    Prev
    Next
    INDEX
    Explanations

    goals and objectives

    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
    Enllaces
    -0.59
     cref
    -0.59
    govine
    -0.55
    RunWith
    -0.53
     plomo
    -0.52
    ibol
    -0.50
    numerusform
    -0.50
     lisäksi
    -0.49
    bleau
    -0.48
    useNewUrlParser
    -0.46
    POSITIVE LOGITS
    principalColumn
    0.74
     for
    0.69
    parsedMessage
    0.60
     TextAlign
    0.59
    fromnode
    0.58
    wahati
    0.58
     ProtoMessage
    0.55
    Portail
    0.54
    complexType
    0.54
     beginnetje
    0.53
    Activations Density 0.002%

    No Known Activations