© 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. 91314
    Prev
    Next
    INDEX
    Explanations

    Occurring after something

    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
     die
    -0.50
     Die
    -0.47
    gefügt
    -0.43
     Mus
    -0.42
    </b>
    -0.42
     Brand
    -0.40
     Ch
    -0.40
     di
    -0.40
     B
    -0.39
     brand
    -0.39
    POSITIVE LOGITS
     myſelf
    0.92
     Efq
    0.84
    operatively
    0.83
    istically
    0.82
     depositphotos
    0.79
     doubtnut
    0.79
    ſelf
    0.79
     Shakspeare
    0.77
     faſt
    0.77
     purpoſe
    0.73
    Activations Density 0.001%

    No Known Activations