© 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. 9445
    Prev
    Next
    INDEX
    Explanations

    concern, worry

    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
     Esau
    -0.55
    findpost
    -0.53
     تانيه
    -0.52
     zijne
    -0.52
    دانشنامهٔ
    -0.51
     becauſe
    -0.50
     coö
    -0.50
     itſelf
    -0.49
    IndentedString
    -0.49
     Phry
    -0.49
    POSITIVE LOGITS
    HostException
    0.66
    LineChart
    0.60
     bağlantılar
    0.50
    vably
    0.50
    listFiles
    0.48
    Ikus
    0.48
    INDER
    0.48
     Bioaccumulative
    0.48
     SwitchCompat
    0.48
    kamera
    0.47
    Activations Density 0.008%

    No Known Activations