© 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. 1-CLT-HP
    7. 9051
    Prev
    Next
    INDEX
    Explanations

    from

    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
    ंदीखरीदारी
    -0.65
    脚注の使い方
    -0.58
     BoxDecoration
    -0.56
    DIPSETTING
    -0.55
    ArrowToggle
    -0.54
    tvguidetime
    -0.53
    :✨
    -0.52
    apimachinery
    -0.51
    charCodeAt
    -0.50
     createSlice
    -0.49
    POSITIVE LOGITS
     envelopes
    0.64
    MessageInfo
    0.59
    Carriera
    0.59
     suffic
    0.59
    ector
    0.58
     being
    0.57
     envelope
    0.56
    tagHelperRunner
    0.54
    HasKey
    0.54
    tud
    0.53
    Activations Density 1.412%

    No Known Activations