© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 91185
    Prev
    Next
    INDEX
    Explanations

    even

    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
     foundation
    -0.81
     raiſ
    -0.65
     Houſe
    -0.64
     Anſ
    -0.63
     ſeveral
    -0.63
     CSL
    -0.61
     doubtnut
    -0.60
     Viter
    -0.60
     Grundlage
    -0.59
    cestry
    -0.59
    POSITIVE LOGITS
    InjectAttribute
    0.72
     betweenstory
    0.66
    WriteTagHelper
    0.65
    OGND
    0.59
    SourceChecksum
    0.58
    GEBURTSDATUM
    0.57
    HideFlags
    0.56
     насељу
    0.54
     Roskov
    0.52
     the
    0.50
    Activations Density 1.100%

    No Known Activations