© 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. 4-CLT-HP
    7. 5043
    Prev
    Next
    INDEX
    Explanations

    have

    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
    fjspx
    -0.49
    NameInMap
    -0.48
     devoirs
    -0.44
     keduanya
    -0.43
    倆
    -0.43
     pair
    -0.42
     our
    -0.41
     Beide
    -0.40
     x
    -0.40
     entrambi
    -0.39
    POSITIVE LOGITS
     JpaRepository
    0.80
     Normdatei
    0.77
     itſelf
    0.67
    Referanser
    0.66
    zież
    0.65
     wives
    0.65
    felves
    0.65
    ArgsConstructor
    0.65
     raiſ
    0.63
    aronder
    0.63
    Activations Density 0.005%

    No Known Activations