© 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. 20-CLT-HP
    7. 77851
    Prev
    Next
    INDEX
    Explanations

    Technical or abstract texts

    np_max-act-logits · 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
    verwijspagina
    -0.65
     JpaRepository
    -0.51
    +#+#
    -0.50
    ]")]
    -0.47
    ]--;
    -0.47
    balleur
    -0.45
    diteur
    -0.45
    Personendaten
    -0.44
     surla
    -0.44
    olstein
    -0.44
    POSITIVE LOGITS
     as
    0.64
    IndentedString
    0.60
    GIVEREF
    0.58
     useAppContext
    0.57
    stylers
    0.54
     Ring
    0.53
     spot
    0.51
     African
    0.50
    为自己
    0.49
     canes
    0.49
    Activations Density 0.000%

    No Known Activations