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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4147
    Prev
    Next
    INDEX
    Explanations

    payment

    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
    TemporalType
    -0.55
    engine
    -0.47
    IRQn
    -0.45
     MEND
    -0.44
    ztus
    -0.43
     moms
    -0.42
    ASTE
    -0.42
     motor
    -0.41
     Obtén
    -0.40
     Validators
    -0.39
    POSITIVE LOGITS
     paille
    0.59
     通販
    0.59
     forward
    0.59
     consideramos
    0.59
    乓
    0.58
    सन्दर्भ
    0.57
    FORWARD
    0.56
    addPreferredGap
    0.56
    forward
    0.55
    kháu
    0.54
    Activations Density 0.003%

    No Known Activations