© 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. 14352
    Prev
    Next
    INDEX
    Explanations

    science

    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
    abestanden
    -0.76
    __*/
    -0.69
    Spoljašnje
    -0.68
    clinic
    -0.66
    });*/
    -0.64
    KURZBESCHREIBUNG
    -0.63
     nonatomic
    -0.62
     referenties
    -0.62
    RefNanny
    -0.62
    Tikang
    -0.62
    POSITIVE LOGITS
    alade
    0.47
    骸
    0.45
    LookAnd
    0.44
     integration
    0.43
    InstanceState
    0.42
     yii
    0.42
     Embedded
    0.42
    postsleuth
    0.41
     Explo
    0.40
     Airborne
    0.40
    Activations Density 0.005%

    No Known Activations