© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 98098
    Prev
    Next
    INDEX
    Explanations

    ,

    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
     itſelf
    -0.81
     myſelf
    -0.68
     anſ
    -0.68
     iſt
    -0.67
     raiſ
    -0.66
     ―――――
    -0.65
    تقاوى
    -0.65
     becauſe
    -0.63
    --}}
    -0.61
    сылкі
    -0.61
    POSITIVE LOGITS
    reactstrap
    0.50
    serializers
    0.48
     OnInit
    0.47
    setattr
    0.45
    UnusedPrivate
    0.44
    openSession
    0.43
     or
    0.43
     JpaRepository
    0.43
    IntoConstraints
    0.42
     Ash
    0.41
    Activations Density 0.006%

    No Known Activations